├── Anaconda2_infos_analysis.ipynb
├── Anaconda3_infos_analysis.ipynb
├── Anaconda环境安装以及搭建Python多内核环境.docx
├── Python_Common_Magic_Samples.ipynb
├── Python_PyODPS_HTML_to_PDF.ipynb
├── Python操作Mysql实例教程手册_代码.ipynb
├── README.md
├── lng_lat_2_geohash_two_way.ipynb
├── post_metas.csv
├── spider_huatu_civil_servant_post_metas.ipynb
├── spider_qiushibaike_content_datas.ipynb
├── spider_qiushibaike_content_datas.py
├── users_rise_up_period.ipynb
└── users_rise_up_period_data


/Anaconda2_infos_analysis.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "### python在数据科学方面需要用到的库：\n",
  8 |     "\n",
  9 |     "- numpy：科学计算库。提供矩阵运算的库。\n",
 10 |     "\n",
 11 |     "- pandas：数据分析处理库\n",
 12 |     "\n",
 13 |     "- scipy：数值计算库。提供数值积分和常微分方程组求解算法。提供了一个非常广泛的特定函数集合。\n",
 14 |     "\n",
 15 |     "- Matplotlib：数据可视化库\n"
 16 |    ]
 17 |   },
 18 |   {
 19 |    "cell_type": "markdown",
 20 |    "metadata": {},
 21 |    "source": [
 22 |     "### 1   当前路径信息（内核Python 2.7）"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "code",
 27 |    "execution_count": 3,
 28 |    "metadata": {},
 29 |    "outputs": [
 30 |     {
 31 |      "data": {
 32 |       "text/plain": [
 33 |        "['',\n",
 34 |        " '/root/anaconda2/lib/python27.zip',\n",
 35 |        " '/root/anaconda2/lib/python2.7',\n",
 36 |        " '/root/anaconda2/lib/python2.7/plat-linux2',\n",
 37 |        " '/root/anaconda2/lib/python2.7/lib-tk',\n",
 38 |        " '/root/anaconda2/lib/python2.7/lib-old',\n",
 39 |        " '/root/anaconda2/lib/python2.7/lib-dynload',\n",
 40 |        " '/root/anaconda2/lib/python2.7/site-packages',\n",
 41 |        " '/root/anaconda2/lib/python2.7/site-packages/Sphinx-1.5.6-py2.7.egg',\n",
 42 |        " '/root/anaconda2/lib/python2.7/site-packages/setuptools-27.2.0-py2.7.egg',\n",
 43 |        " '/root/anaconda2/lib/python2.7/site-packages/IPython/extensions',\n",
 44 |        " '/root/.ipython']"
 45 |       ]
 46 |      },
 47 |      "execution_count": 3,
 48 |      "metadata": {},
 49 |      "output_type": "execute_result"
 50 |     }
 51 |    ],
 52 |    "source": [
 53 |     "import sys\n",
 54 |     "\n",
 55 |     "sys.path"
 56 |    ]
 57 |   },
 58 |   {
 59 |    "cell_type": "markdown",
 60 |    "metadata": {},
 61 |    "source": [
 62 |     "### 2  科学计算常用包版本及路径信息"
 63 |    ]
 64 |   },
 65 |   {
 66 |    "cell_type": "code",
 67 |    "execution_count": 4,
 68 |    "metadata": {},
 69 |    "outputs": [
 70 |     {
 71 |      "data": {
 72 |       "text/html": [
 73 |        "<div>\n",
 74 |        "<style>\n",
 75 |        "    .dataframe thead tr:only-child th {\n",
 76 |        "        text-align: right;\n",
 77 |        "    }\n",
 78 |        "\n",
 79 |        "    .dataframe thead th {\n",
 80 |        "        text-align: left;\n",
 81 |        "    }\n",
 82 |        "\n",
 83 |        "    .dataframe tbody tr th {\n",
 84 |        "        vertical-align: top;\n",
 85 |        "    }\n",
 86 |        "</style>\n",
 87 |        "<table border=\"1\" class=\"dataframe\">\n",
 88 |        "  <thead>\n",
 89 |        "    <tr style=\"text-align: right;\">\n",
 90 |        "      <th></th>\n",
 91 |        "      <th>pack_name</th>\n",
 92 |        "      <th>version</th>\n",
 93 |        "      <th>path</th>\n",
 94 |        "    </tr>\n",
 95 |        "  </thead>\n",
 96 |        "  <tbody>\n",
 97 |        "    <tr>\n",
 98 |        "      <th>0</th>\n",
 99 |        "      <td>numpy</td>\n",
100 |        "      <td>1.12.1</td>\n",
101 |        "      <td>/root/anaconda2/lib/python2.7/site-packages/numpy/__init__.pyc</td>\n",
102 |        "    </tr>\n",
103 |        "    <tr>\n",
104 |        "      <th>1</th>\n",
105 |        "      <td>matplotlib</td>\n",
106 |        "      <td>2.0.2</td>\n",
107 |        "      <td>/root/anaconda2/lib/python2.7/site-packages/matplotlib/__init__.pyc</td>\n",
108 |        "    </tr>\n",
109 |        "    <tr>\n",
110 |        "      <th>2</th>\n",
111 |        "      <td>pandas</td>\n",
112 |        "      <td>0.20.1</td>\n",
113 |        "      <td>/root/anaconda2/lib/python2.7/site-packages/pandas/__init__.pyc</td>\n",
114 |        "    </tr>\n",
115 |        "    <tr>\n",
116 |        "      <th>3</th>\n",
117 |        "      <td>scipy</td>\n",
118 |        "      <td>0.19.0</td>\n",
119 |        "      <td>/root/anaconda2/lib/python2.7/site-packages/scipy/__init__.pyc</td>\n",
120 |        "    </tr>\n",
121 |        "  </tbody>\n",
122 |        "</table>\n",
123 |        "</div>"
124 |       ],
125 |       "text/plain": [
126 |        "    pack_name version  \\\n",
127 |        "0       numpy  1.12.1   \n",
128 |        "1  matplotlib   2.0.2   \n",
129 |        "2      pandas  0.20.1   \n",
130 |        "3       scipy  0.19.0   \n",
131 |        "\n",
132 |        "                                                                  path  \n",
133 |        "0       /root/anaconda2/lib/python2.7/site-packages/numpy/__init__.pyc  \n",
134 |        "1  /root/anaconda2/lib/python2.7/site-packages/matplotlib/__init__.pyc  \n",
135 |        "2      /root/anaconda2/lib/python2.7/site-packages/pandas/__init__.pyc  \n",
136 |        "3       /root/anaconda2/lib/python2.7/site-packages/scipy/__init__.pyc  "
137 |       ]
138 |      },
139 |      "execution_count": 4,
140 |      "metadata": {},
141 |      "output_type": "execute_result"
142 |     }
143 |    ],
144 |    "source": [
145 |     "import numpy\n",
146 |     "import matplotlib\n",
147 |     "import pandas as pd\n",
148 |     "import scipy\n",
149 |     "\n",
150 |     "packs = [\n",
151 |     "    (\"numpy\", numpy.__version__, numpy.__file__),\n",
152 |     "    (\"matplotlib\", matplotlib.__version__, matplotlib.__file__),\n",
153 |     "    (\"pandas\", pd.__version__, pd.__file__),\n",
154 |     "    (\"scipy\", scipy.__version__, scipy.__file__)\n",
155 |     "]\n",
156 |     "\n",
157 |     "pd_packages = pd.DataFrame(packs, columns=[\"pack_name\", \"version\", \"path\"])\n",
158 |     "pd.set_option(\"max_colwidth\", 120)\n",
159 |     "pd_packages"
160 |    ]
161 |   },
162 |   {
163 |    "cell_type": "markdown",
164 |    "metadata": {},
165 |    "source": [
166 |     "### 3  Anaconda2 集成包简单分析"
167 |    ]
168 |   },
169 |   {
170 |    "cell_type": "code",
171 |    "execution_count": 10,
172 |    "metadata": {
173 |     "collapsed": true
174 |    },
175 |    "outputs": [],
176 |    "source": [
177 |     "import sys\n",
178 |     "%matplotlib inline\n",
179 |     "\n",
180 |     "packages = [pack.split(\".\")[0] for pack in sys.modules.keys()]\n",
181 |     "pd_packages = pd.DataFrame(packages, columns=[\"package\"])\n",
182 |     "pack_series = pd_packages.groupby(by=\"package\").size()"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": 11,
188 |    "metadata": {},
189 |    "outputs": [
190 |     {
191 |      "data": {
192 |       "text/plain": [
193 |        "count    214.000000\n",
194 |        "mean      10.163551\n",
195 |        "std       37.323436\n",
196 |        "min        1.000000\n",
197 |        "25%        1.000000\n",
198 |        "50%        1.000000\n",
199 |        "75%        1.000000\n",
200 |        "max      411.000000\n",
201 |        "dtype: float64"
202 |       ]
203 |      },
204 |      "execution_count": 11,
205 |      "metadata": {},
206 |      "output_type": "execute_result"
207 |     }
208 |    ],
209 |    "source": [
210 |     "pack_series.describe()"
211 |    ]
212 |   },
213 |   {
214 |    "cell_type": "code",
215 |    "execution_count": 12,
216 |    "metadata": {},
217 |    "outputs": [
218 |     {
219 |      "data": {
220 |       "text/plain": [
221 |        "214"
222 |       ]
223 |      },
224 |      "execution_count": 12,
225 |      "metadata": {},
226 |      "output_type": "execute_result"
227 |     }
228 |    ],
229 |    "source": [
230 |     "pack_series.index.duplicated()\n",
231 |     "pack_temp = pack_series.index.drop_duplicates()\n",
232 |     "len(pack_temp)"
233 |    ]
234 |   },
235 |   {
236 |    "cell_type": "markdown",
237 |    "metadata": {},
238 |    "source": [
239 |     "### 3.1  根据 Anaconda 2包中的模块数量倒序 绘图"
240 |    ]
241 |   },
242 |   {
243 |    "cell_type": "code",
244 |    "execution_count": 14,
245 |    "metadata": {},
246 |    "outputs": [
247 |     {
248 |      "data": {
249 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEKCAYAAAAcgp5RAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
250 |       "text/plain": [
251 |        "<matplotlib.figure.Figure at 0x7f861ae758d0>"
252 |       ]
253 |      },
254 |      "metadata": {},
255 |      "output_type": "display_data"
256 |     }
257 |    ],
258 |    "source": [
259 |     "pack_series.sort_values(ascending=False)[:50].plot();"
260 |    ]
261 |   },
262 |   {
263 |    "cell_type": "code",
264 |    "execution_count": 9,
265 |    "metadata": {},
266 |    "outputs": [
267 |     {
268 |      "data": {
269 |       "text/plain": [
270 |        "package\n",
271 |        "pandas            406\n",
272 |        "IPython           263\n",
273 |        "prompt_toolkit    146\n",
274 |        "matplotlib         92\n",
275 |        "_pytest            91\n",
276 |        "numpy              87\n",
277 |        "ipykernel          71\n",
278 |        "zmq                66\n",
279 |        "jupyter_client     52\n",
280 |        "py                 51\n",
281 |        "xlsxwriter         50\n",
282 |        "email              49\n",
283 |        "pygments           49\n",
284 |        "ipywidgets         42\n",
285 |        "pkg_resources      42\n",
286 |        "traitlets          42\n",
287 |        "dateutil           35\n",
288 |        "bottleneck         27\n",
289 |        "numexpr            25\n",
290 |        "unittest           24\n",
291 |        "dtype: int64"
292 |       ]
293 |      },
294 |      "execution_count": 9,
295 |      "metadata": {},
296 |      "output_type": "execute_result"
297 |     }
298 |    ],
299 |    "source": [
300 |     "pack_series.sort_values(ascending=False)[:20]"
301 |    ]
302 |   },
303 |   {
304 |    "cell_type": "markdown",
305 |    "metadata": {},
306 |    "source": [
307 |     "### 3.2  Aanaconda 2 中模块信息"
308 |    ]
309 |   },
310 |   {
311 |    "cell_type": "code",
312 |    "execution_count": null,
313 |    "metadata": {
314 |     "scrolled": false
315 |    },
316 |    "outputs": [
317 |     {
318 |      "name": "stdout",
319 |      "output_type": "stream",
320 |      "text": [
321 |       "\n",
322 |       "Please wait a moment while I gather a list of all available modules...\n",
323 |       "\n"
324 |      ]
325 |     },
326 |     {
327 |      "name": "stderr",
328 |      "output_type": "stream",
329 |      "text": [
330 |       "/root/anaconda2/lib/python2.7/site-packages/IPython/kernel/__init__.py:13: ShimWarning: The `IPython.kernel` package has been deprecated since IPython 4.0.You should import from ipykernel or jupyter_client instead.\n",
331 |       "  \"You should import from ipykernel or jupyter_client instead.\", ShimWarning)\n",
332 |       "/root/anaconda2/lib/python2.7/site-packages/odo/backends/pandas.py:94: FutureWarning: pandas.tslib is deprecated and will be removed in a future version.\n",
333 |       "You can access NaTType as type(pandas.NaT)\n",
334 |       "  @convert.register((pd.Timestamp, pd.Timedelta), (pd.tslib.NaTType, type(None)))\n",
335 |       "/root/anaconda2/lib/python2.7/site-packages/blaze/server/server.py:17: ExtDeprecationWarning: Importing flask.ext.cors is deprecated, use flask_cors instead.\n",
336 |       "  from flask.ext.cors import cross_origin\n",
337 |       "/root/anaconda2/lib/python2.7/site-packages/bokeh/util/deprecation.py:34: BokehDeprecationWarning: MPL compatibility can no longer be successfully maintained, and is now deprecated. All MPL compat functions will be removed completely on the release of Bokeh 1.0. See http://bokeh.pydata.org/en/latest/docs/releases/0.12.5.html for more information\n",
338 |       "  warn(message)\n",
339 |       "/root/anaconda2/lib/python2.7/site-packages/matplotlib/cbook.py:136: MatplotlibDeprecationWarning: The matplotlib.delaunay module was deprecated in version 1.4. Use matplotlib.tri.Triangulation instead.\n",
340 |       "  warnings.warn(message, mplDeprecation, stacklevel=1)\n",
341 |       "/root/anaconda2/lib/python2.7/site-packages/nltk/twitter/__init__.py:20: UserWarning: The twython library has not been installed. Some functionality from the twitter package will not be available.\n",
342 |       "  warnings.warn(\"The twython library has not been installed. \"\n",
343 |       "/root/anaconda2/lib/python2.7/site-packages/skimage/viewer/utils/core.py:10: UserWarning: Recommended matplotlib backend is `Agg` for full skimage.viewer functionality.\n",
344 |       "  warn(\"Recommended matplotlib backend is `Agg` for full \"\n",
345 |       "/root/anaconda2/lib/python2.7/site-packages/qtawesome/iconic_font.py:268: UserWarning: You need to have a running QApplication to use QtAwesome!\n",
346 |       "  warnings.warn(\"You need to have a running \"\n",
347 |       "/root/anaconda2/lib/python2.7/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.\n",
348 |       "  from pandas.core import datetools\n"
349 |      ]
350 |     },
351 |     {
352 |      "name": "stdout",
353 |      "output_type": "stream",
354 |      "text": [
355 |       "BaseHTTPServer      bs4                 jupyter_core        scripts\n",
356 |       "Bastion             bsddb               keyword             seaborn\n",
357 |       "CDROM               bz2                 lazy_object_proxy   select\n",
358 |       "CGIHTTPServer       cPickle             lib2to3             sets\n",
359 |       "Canvas              cProfile            linecache           setuptools\n",
360 |       "ConfigParser        cStringIO           linuxaudiodev       sgmllib\n",
361 |       "Cookie              cairo               llvmlite            sha\n",
362 |       "Crypto              calendar            locale              shelve\n",
363 |       "Cython              cdecimal            locket              shlex\n",
364 |       "DLFCN               cffi                logging             shutil\n",
365 |       "Dialog              cgi                 lxml                signal\n",
366 |       "DocXMLRPCServer     cgitb               macpath             simplegeneric\n",
367 |       "FileDialog          chardet             macurl2path         singledispatch\n",
368 |       "FixTk               chunk               mailbox             singledispatch_helpers\n",
369 |       "HTMLParser          click               mailcap             sip\n",
370 |       "IN                  cloudpickle         markupbase          sipconfig\n",
371 |       "IPython             clyent              markupsafe          sipdistutils\n",
372 |       "MimeWriter          cmath               marshal             site\n",
373 |       "OleFileIO_PL        cmd                 math                six\n",
374 |       "OpenSSL             code                matplotlib          skimage\n",
375 |       "PIL                 codecs              md5                 sklearn\n",
376 |       "PyQt5               codeop              mhlib               smtpd\n",
377 |       "Queue               collections         mimetools           smtplib\n",
378 |       "ScrolledText        colorama            mimetypes           sndhdr\n",
379 |       "SimpleDialog        colorsys            mimify              snowballstemmer\n",
380 |       "SimpleHTTPServer    command             mistune             socket\n",
381 |       "SimpleXMLRPCServer  commands            mkl                 sortedcollections\n",
382 |       "SocketServer        compileall          mmap                sortedcontainers\n",
383 |       "StringIO            compiler            modulefinder        sphinx\n",
384 |       "TYPES               concurrent          mpl_toolkits        spwd\n",
385 |       "Tix                 conda               mpmath              spyder\n",
386 |       "Tkconstants         conda_env           msgpack             spyder_breakpoints\n",
387 |       "Tkdnd               configparser        multifile           spyder_io_dcm\n",
388 |       "Tkinter             contextlib          multipledispatch    spyder_io_hdf5\n",
389 |       "UserDict            contextlib2         multiprocessing     spyder_profiler\n",
390 |       "UserList            cookielib           mutex               spyder_pylint\n",
391 |       "UserString          copy                navigator_updater   sqlalchemy\n",
392 |       "_LWPCookieJar       copy_reg            nbconvert           sqlite3\n",
393 |       "_MozillaCookieJar   crypt               nbformat            sre\n",
394 |       "__builtin__         cryptography        netrc               sre_compile\n",
395 |       "__future__          csv                 networkx            sre_constants\n",
396 |       "_abcoll             ctypes              new                 sre_parse\n",
397 |       "_ast                curl                nis                 ssl\n",
398 |       "_bisect             curses              nltk                stat\n",
399 |       "_cffi_backend       cycler              nntplib             statsmodels\n",
400 |       "_codecs             cython              nose                statvfs\n",
401 |       "_codecs_cn          cythonmagic         notebook            storemagic\n",
402 |       "_codecs_hk          cytoolz             ntpath              string\n",
403 |       "_codecs_iso2022     dask                nturl2path          stringold\n",
404 |       "_codecs_jp          datashape           numba               stringprep\n",
405 |       "_codecs_kr          datetime            numbers             strop\n",
406 |       "_codecs_tw          dateutil            numexpr             struct\n",
407 |       "_collections        dbhash              numpy               subprocess\n",
408 |       "_csv                decimal             numpydoc            subprocess32\n",
409 |       "_ctypes             decorator           odo                 sunau\n",
410 |       "_ctypes_test        difflib             olefile             sunaudio\n",
411 |       "_curses             dircache            opcode              symbol\n",
412 |       "_curses_panel       dis                 openpyxl            sympy\n",
413 |       "_elementtree        distributed         operator            sympyprinting\n",
414 |       "_functools          distutils           optparse            symtable\n",
415 |       "_hashlib            doctest             os                  sys\n",
416 |       "_heapq              docutils            os2emxpath          sysconfig\n",
417 |       "_hotshot            dumbdbm             ossaudiodev         syslog\n",
418 |       "_io                 dummy_thread        packaging           tables\n",
419 |       "_json               dummy_threading     pandas              tabnanny\n",
420 |       "_license            easy_install        pandocfilters       tarfile\n",
421 |       "_locale             email               parser              tblib\n",
422 |       "_lsprof             encodings           partd               telnetlib\n",
423 |       "_multibytecodec     entrypoints         path                tempfile\n",
424 |       "_multiprocessing    enum                pathlib2            terminado\n",
425 |       "_osx_support        errno               patsy               termios\n",
426 |       "_posixsubprocess    et_xmlfile          pdb                 test_path\n",
427 |       "_pyio               exceptions          pep8                test_pycosat\n",
428 |       "_pytest             extern              pexpect             testpath\n",
429 |       "_random             fastcache           pickle              tests\n",
430 |       "_scandir            fcntl               pickleshare         textwrap\n",
431 |       "_socket             filecmp             pickletools         this\n",
432 |       "_sqlite3            fileinput           pip                 thread\n",
433 |       "_sre                flask               pipes               threading\n",
434 |       "_ssl                flask_cors          pkg_resources       time\n",
435 |       "_strptime           fnmatch             pkgutil             timeit\n",
436 |       "_struct             formatter           platform            tkColorChooser\n",
437 |       "_symtable           fpformat            plistlib            tkCommonDialog\n",
438 |       "_sysconfigdata      fractions           ply                 tkFileDialog\n",
439 |       "_testcapi           ftplib              popen2              tkFont\n",
440 |       "_threading_local    funcsigs            poplib              tkMessageBox\n",
441 |       "_tkinter            functools           posix               tkSimpleDialog\n",
442 |       "_vendor             functools32         posixfile           tlz\n",
443 |       "_warnings           future_builtins     posixpath           toaiff\n",
444 |       "_weakref            gc                  pprint              token\n",
445 |       "_weakrefset         genericpath         profile             tokenize\n",
446 |       "_yaml               getopt              prompt_toolkit      toolz\n",
447 |       "abc                 getpass             pstats              tornado\n",
448 |       "aifc                gettext             psutil              trace\n",
449 |       "alabaster           gevent              pty                 traceback\n",
450 |       "anaconda_navigator  glob                ptyprocess          traitlets\n",
451 |       "anaconda_project    greenlet            pwd                 ttk\n",
452 |       "antigravity         grin                py                  tty\n",
453 |       "anydbm              grp                 py_compile          turtle\n",
454 |       "argparse            gzip                pyclbr              types\n",
455 |       "array               h5py                pycosat             unicodecsv\n",
456 |       "asn1crypto          hashlib             pycparser           unicodedata\n",
457 |       "ast                 heapdict            pycurl              unittest\n",
458 |       "astroid             heapq               pydoc               urllib\n",
459 |       "astropy             hmac                pydoc_data          urllib2\n",
460 |       "asynchat            hotshot             pyexpat             urlparse\n",
461 |       "asyncore            html5lib            pyflakes            user\n",
462 |       "atexit              htmlentitydefs      pygments            uu\n",
463 |       "audiodev            htmllib             pylab               uuid\n",
464 |       "audioop             httplib             pylint              warnings\n",
465 |       "autoreload          idlelib             pyodbc              wave\n",
466 |       "babel               idna                pyparsing           wcwidth\n",
467 |       "backports           ihooks              pytest              weakref\n",
468 |       "backports_abc       imagesize           pytz                webbrowser\n",
469 |       "base64              imaplib             pywt                werkzeug\n",
470 |       "bdb                 imghdr              pyximport           wheel\n",
471 |       "binascii            imp                 qtawesome           whichdb\n",
472 |       "binhex              importlib           qtconsole           widgetsnbextension\n",
473 |       "binstar_client      imputil             qtpy                wrapt\n",
474 |       "bisect              inspect             quopri              wsgiref\n",
475 |       "bitarray            io                  random              xdrlib\n",
476 |       "blaze               ipaddress           re                  xlrd\n",
477 |       "bleach              ipykernel           readline            xlsxwriter\n",
478 |       "bokeh               ipykernel_launcher  repr                xlwt\n",
479 |       "boto                ipython_genutils    requests            xml\n",
480 |       "bottleneck          ipywidgets          resource            xmllib\n",
481 |       "brain_builtin_inference isort               rexec               xmlrpclib\n",
482 |       "brain_dateutil      itertools           rfc822              xxsubtype\n",
483 |       "brain_gi            itsdangerous        rlcompleter         yaml\n",
484 |       "brain_mechanize     jdcal               rmagic              zict\n",
485 |       "brain_nose          jedi                robotparser         zipfile\n",
486 |       "brain_numpy         jinja2              rope                zipimport\n",
487 |       "brain_pytest        json                ruamel_yaml         zlib\n",
488 |       "brain_qt            jsonschema          runpy               zmq\n",
489 |       "brain_six           jupyter             scandir             \n",
490 |       "brain_ssl           jupyter_client      sched               \n",
491 |       "brain_stdlib        jupyter_console     scipy               \n",
492 |       "\n",
493 |       "Enter any module name to get more help.  Or, type \"modules spam\" to search\n",
494 |       "for modules whose descriptions contain the word \"spam\".\n",
495 |       "\n"
496 |      ]
497 |     }
498 |    ],
499 |    "source": [
500 |     "help(\"modules\")"
501 |    ]
502 |   }
503 |  ],
504 |  "metadata": {
505 |   "kernelspec": {
506 |    "display_name": "Python 2",
507 |    "language": "python",
508 |    "name": "python2.7"
509 |   },
510 |   "language_info": {
511 |    "codemirror_mode": {
512 |     "name": "ipython",
513 |     "version": 2
514 |    },
515 |    "file_extension": ".py",
516 |    "mimetype": "text/x-python",
517 |    "name": "python",
518 |    "nbconvert_exporter": "python",
519 |    "pygments_lexer": "ipython2",
520 |    "version": "2.7.13"
521 |   }
522 |  },
523 |  "nbformat": 4,
524 |  "nbformat_minor": 2
525 | }
526 | 


--------------------------------------------------------------------------------
/Anaconda3_infos_analysis.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "### python在数据科学方面需要用到的库：\n",
  8 |     "\n",
  9 |     "- numpy：科学计算库。提供矩阵运算的库。\n",
 10 |     "\n",
 11 |     "- pandas：数据分析处理库\n",
 12 |     "\n",
 13 |     "- scipy：数值计算库。提供数值积分和常微分方程组求解算法。提供了一个非常广泛的特定函数集合。\n",
 14 |     "\n",
 15 |     "- Matplotlib：数据可视化库\n"
 16 |    ]
 17 |   },
 18 |   {
 19 |    "cell_type": "markdown",
 20 |    "metadata": {},
 21 |    "source": [
 22 |     "### 1   当前路径信息（内核Python 3.6）"
 23 |    ]
 24 |   },
 25 |   {
 26 |    "cell_type": "code",
 27 |    "execution_count": 1,
 28 |    "metadata": {},
 29 |    "outputs": [
 30 |     {
 31 |      "data": {
 32 |       "text/plain": [
 33 |        "['',\n",
 34 |        " '/root/anaconda3/lib/python36.zip',\n",
 35 |        " '/root/anaconda3/lib/python3.6',\n",
 36 |        " '/root/anaconda3/lib/python3.6/lib-dynload',\n",
 37 |        " '/root/anaconda3/lib/python3.6/site-packages',\n",
 38 |        " '/root/anaconda3/lib/python3.6/site-packages/Sphinx-1.5.6-py3.6.egg',\n",
 39 |        " '/root/anaconda3/lib/python3.6/site-packages/setuptools-27.2.0-py3.6.egg',\n",
 40 |        " '/root/anaconda3/lib/python3.6/site-packages/IPython/extensions',\n",
 41 |        " '/root/.ipython']"
 42 |       ]
 43 |      },
 44 |      "execution_count": 1,
 45 |      "metadata": {},
 46 |      "output_type": "execute_result"
 47 |     }
 48 |    ],
 49 |    "source": [
 50 |     "import sys\n",
 51 |     "\n",
 52 |     "sys.path"
 53 |    ]
 54 |   },
 55 |   {
 56 |    "cell_type": "markdown",
 57 |    "metadata": {},
 58 |    "source": [
 59 |     "### 2  科学计算常用包版本及路径信息"
 60 |    ]
 61 |   },
 62 |   {
 63 |    "cell_type": "code",
 64 |    "execution_count": 3,
 65 |    "metadata": {},
 66 |    "outputs": [
 67 |     {
 68 |      "data": {
 69 |       "text/html": [
 70 |        "<div>\n",
 71 |        "<style>\n",
 72 |        "    .dataframe thead tr:only-child th {\n",
 73 |        "        text-align: right;\n",
 74 |        "    }\n",
 75 |        "\n",
 76 |        "    .dataframe thead th {\n",
 77 |        "        text-align: left;\n",
 78 |        "    }\n",
 79 |        "\n",
 80 |        "    .dataframe tbody tr th {\n",
 81 |        "        vertical-align: top;\n",
 82 |        "    }\n",
 83 |        "</style>\n",
 84 |        "<table border=\"1\" class=\"dataframe\">\n",
 85 |        "  <thead>\n",
 86 |        "    <tr style=\"text-align: right;\">\n",
 87 |        "      <th></th>\n",
 88 |        "      <th>pack_name</th>\n",
 89 |        "      <th>version</th>\n",
 90 |        "      <th>path</th>\n",
 91 |        "    </tr>\n",
 92 |        "  </thead>\n",
 93 |        "  <tbody>\n",
 94 |        "    <tr>\n",
 95 |        "      <th>0</th>\n",
 96 |        "      <td>numpy</td>\n",
 97 |        "      <td>1.12.1</td>\n",
 98 |        "      <td>/root/anaconda3/lib/python3.6/site-packages/numpy/__init__.py</td>\n",
 99 |        "    </tr>\n",
100 |        "    <tr>\n",
101 |        "      <th>1</th>\n",
102 |        "      <td>matplotlib</td>\n",
103 |        "      <td>2.0.2</td>\n",
104 |        "      <td>/root/anaconda3/lib/python3.6/site-packages/matplotlib/__init__.py</td>\n",
105 |        "    </tr>\n",
106 |        "    <tr>\n",
107 |        "      <th>2</th>\n",
108 |        "      <td>pandas</td>\n",
109 |        "      <td>0.20.1</td>\n",
110 |        "      <td>/root/anaconda3/lib/python3.6/site-packages/pandas/__init__.py</td>\n",
111 |        "    </tr>\n",
112 |        "    <tr>\n",
113 |        "      <th>3</th>\n",
114 |        "      <td>scipy</td>\n",
115 |        "      <td>0.19.0</td>\n",
116 |        "      <td>/root/anaconda3/lib/python3.6/site-packages/scipy/__init__.py</td>\n",
117 |        "    </tr>\n",
118 |        "  </tbody>\n",
119 |        "</table>\n",
120 |        "</div>"
121 |       ],
122 |       "text/plain": [
123 |        "    pack_name version  \\\n",
124 |        "0       numpy  1.12.1   \n",
125 |        "1  matplotlib   2.0.2   \n",
126 |        "2      pandas  0.20.1   \n",
127 |        "3       scipy  0.19.0   \n",
128 |        "\n",
129 |        "                                                                 path  \n",
130 |        "0       /root/anaconda3/lib/python3.6/site-packages/numpy/__init__.py  \n",
131 |        "1  /root/anaconda3/lib/python3.6/site-packages/matplotlib/__init__.py  \n",
132 |        "2      /root/anaconda3/lib/python3.6/site-packages/pandas/__init__.py  \n",
133 |        "3       /root/anaconda3/lib/python3.6/site-packages/scipy/__init__.py  "
134 |       ]
135 |      },
136 |      "execution_count": 3,
137 |      "metadata": {},
138 |      "output_type": "execute_result"
139 |     }
140 |    ],
141 |    "source": [
142 |     "import numpy\n",
143 |     "import matplotlib\n",
144 |     "import pandas as pd\n",
145 |     "import scipy\n",
146 |     "\n",
147 |     "packs = [\n",
148 |     "    (\"numpy\", numpy.__version__, numpy.__file__),\n",
149 |     "    (\"matplotlib\", matplotlib.__version__, matplotlib.__file__),\n",
150 |     "    (\"pandas\", pd.__version__, pd.__file__),\n",
151 |     "    (\"scipy\", scipy.__version__, scipy.__file__)\n",
152 |     "]\n",
153 |     "\n",
154 |     "pd_packages = pd.DataFrame(packs, columns=[\"pack_name\", \"version\", \"path\"])\n",
155 |     "pd.set_option(\"max_colwidth\", 120)\n",
156 |     "pd_packages"
157 |    ]
158 |   },
159 |   {
160 |    "cell_type": "markdown",
161 |    "metadata": {},
162 |    "source": [
163 |     "### 3  Anaconda3 集成包简单分析"
164 |    ]
165 |   },
166 |   {
167 |    "cell_type": "code",
168 |    "execution_count": 4,
169 |    "metadata": {
170 |     "collapsed": true
171 |    },
172 |    "outputs": [],
173 |    "source": [
174 |     "import sys\n",
175 |     "%matplotlib inline\n",
176 |     "\n",
177 |     "packages = [pack.split(\".\")[0] for pack in sys.modules.keys()]\n",
178 |     "pd_packages = pd.DataFrame(packages, columns=[\"package\"])\n",
179 |     "pack_series = pd_packages.groupby(by=\"package\").size()"
180 |    ]
181 |   },
182 |   {
183 |    "cell_type": "code",
184 |    "execution_count": 5,
185 |    "metadata": {},
186 |    "outputs": [
187 |     {
188 |      "data": {
189 |       "text/plain": [
190 |        "count    229.000000\n",
191 |        "mean       4.978166\n",
192 |        "std       16.714697\n",
193 |        "min        1.000000\n",
194 |        "25%        1.000000\n",
195 |        "50%        1.000000\n",
196 |        "75%        1.000000\n",
197 |        "max      169.000000\n",
198 |        "dtype: float64"
199 |       ]
200 |      },
201 |      "execution_count": 5,
202 |      "metadata": {},
203 |      "output_type": "execute_result"
204 |     }
205 |    ],
206 |    "source": [
207 |     "pack_series.describe()"
208 |    ]
209 |   },
210 |   {
211 |    "cell_type": "code",
212 |    "execution_count": 6,
213 |    "metadata": {},
214 |    "outputs": [
215 |     {
216 |      "data": {
217 |       "text/plain": [
218 |        "229"
219 |       ]
220 |      },
221 |      "execution_count": 6,
222 |      "metadata": {},
223 |      "output_type": "execute_result"
224 |     }
225 |    ],
226 |    "source": [
227 |     "pack_series.index.duplicated()\n",
228 |     "pack_temp = pack_series.index.drop_duplicates()\n",
229 |     "len(pack_temp)"
230 |    ]
231 |   },
232 |   {
233 |    "cell_type": "markdown",
234 |    "metadata": {},
235 |    "source": [
236 |     "### 3.1  根据 Anaconda 3包中的模块数量倒序 绘图"
237 |    ]
238 |   },
239 |   {
240 |    "cell_type": "code",
241 |    "execution_count": 10,
242 |    "metadata": {},
243 |    "outputs": [
244 |     {
245 |      "data": {
246 |       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEKCAYAAAAcgp5RAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nSpyD3sysxDnozcxKnIPezKzE/Q/9/LoiMkkCBQAAAABJRU5ErkJggg==\n",
247 |       "text/plain": [
248 |        "<matplotlib.figure.Figure at 0x7fdc918c1438>"
249 |       ]
250 |      },
251 |      "metadata": {},
252 |      "output_type": "display_data"
253 |     }
254 |    ],
255 |    "source": [
256 |     "pack_series.sort_values(ascending=False)[:50].plot();"
257 |    ]
258 |   },
259 |   {
260 |    "cell_type": "code",
261 |    "execution_count": 11,
262 |    "metadata": {},
263 |    "outputs": [
264 |     {
265 |      "data": {
266 |       "text/plain": [
267 |        "package\n",
268 |        "pandas            169\n",
269 |        "IPython           118\n",
270 |        "matplotlib         85\n",
271 |        "numpy              82\n",
272 |        "prompt_toolkit     70\n",
273 |        "_pytest            36\n",
274 |        "xlsxwriter         32\n",
275 |        "zmq                31\n",
276 |        "ipywidgets         25\n",
277 |        "py                 25\n",
278 |        "ipykernel          23\n",
279 |        "pygments           20\n",
280 |        "jupyter_client     19\n",
281 |        "pkg_resources      18\n",
282 |        "bottleneck         17\n",
283 |        "dtype: int64"
284 |       ]
285 |      },
286 |      "execution_count": 11,
287 |      "metadata": {},
288 |      "output_type": "execute_result"
289 |     }
290 |    ],
291 |    "source": [
292 |     "pack_series.sort_values(ascending=False)[:15]"
293 |    ]
294 |   },
295 |   {
296 |    "cell_type": "markdown",
297 |    "metadata": {},
298 |    "source": [
299 |     "### 3.2  Aanaconda 3 中模块信息"
300 |    ]
301 |   },
302 |   {
303 |    "cell_type": "code",
304 |    "execution_count": 14,
305 |    "metadata": {
306 |     "scrolled": false
307 |    },
308 |    "outputs": [
309 |     {
310 |      "name": "stdout",
311 |      "output_type": "stream",
312 |      "text": [
313 |       "\n",
314 |       "Please wait a moment while I gather a list of all available modules...\n",
315 |       "\n"
316 |      ]
317 |     },
318 |     {
319 |      "name": "stderr",
320 |      "output_type": "stream",
321 |      "text": [
322 |       "/root/anaconda3/lib/python3.6/site-packages/IPython/kernel/__init__.py:13: ShimWarning: The `IPython.kernel` package has been deprecated since IPython 4.0.You should import from ipykernel or jupyter_client instead.\n",
323 |       "  \"You should import from ipykernel or jupyter_client instead.\", ShimWarning)\n",
324 |       "/root/anaconda3/lib/python3.6/site-packages/odo/backends/pandas.py:94: FutureWarning: pandas.tslib is deprecated and will be removed in a future version.\n",
325 |       "You can access NaTType as type(pandas.NaT)\n",
326 |       "  @convert.register((pd.Timestamp, pd.Timedelta), (pd.tslib.NaTType, type(None)))\n",
327 |       "/root/anaconda3/lib/python3.6/site-packages/blaze/server/server.py:17: ExtDeprecationWarning: Importing flask.ext.cors is deprecated, use flask_cors instead.\n",
328 |       "  from flask.ext.cors import cross_origin\n",
329 |       "/root/anaconda3/lib/python3.6/site-packages/bokeh/util/deprecation.py:34: BokehDeprecationWarning: MPL compatibility can no longer be successfully maintained, and is now deprecated. All MPL compat functions will be removed completely on the release of Bokeh 1.0. See http://bokeh.pydata.org/en/latest/docs/releases/0.12.5.html for more information\n",
330 |       "  warn(message)\n",
331 |       "/root/anaconda3/lib/python3.6/site-packages/matplotlib/cbook.py:136: MatplotlibDeprecationWarning: The matplotlib.delaunay module was deprecated in version 1.4. Use matplotlib.tri.Triangulation instead.\n",
332 |       "  warnings.warn(message, mplDeprecation, stacklevel=1)\n",
333 |       "/root/anaconda3/lib/python3.6/site-packages/nltk/twitter/__init__.py:20: UserWarning: The twython library has not been installed. Some functionality from the twitter package will not be available.\n",
334 |       "  warnings.warn(\"The twython library has not been installed. \"\n",
335 |       "/root/anaconda3/lib/python3.6/site-packages/skimage/viewer/utils/core.py:10: UserWarning: Recommended matplotlib backend is `Agg` for full skimage.viewer functionality.\n",
336 |       "  warn(\"Recommended matplotlib backend is `Agg` for full \"\n",
337 |       "/root/anaconda3/lib/python3.6/site-packages/qtawesome/iconic_font.py:268: UserWarning: You need to have a running QApplication to use QtAwesome!\n",
338 |       "  warnings.warn(\"You need to have a running \"\n",
339 |       "/root/anaconda3/lib/python3.6/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.\n",
340 |       "  from pandas.core import datetools\n"
341 |      ]
342 |     },
343 |     {
344 |      "name": "stdout",
345 |      "output_type": "stream",
346 |      "text": [
347 |       "Crypto              brain_nose          jupyter_core        scipy\n",
348 |       "Cython              brain_numpy         keyword             scripts\n",
349 |       "IPython             brain_pytest        lazy_object_proxy   seaborn\n",
350 |       "OleFileIO_PL        brain_qt            lib2to3             secrets\n",
351 |       "OpenSSL             brain_six           linecache           select\n",
352 |       "PIL                 brain_ssl           llvmlite            selectors\n",
353 |       "PyQt5               brain_stdlib        locale              setuptools\n",
354 |       "__future__          bs4                 locket              shelve\n",
355 |       "_ast                builtins            logging             shlex\n",
356 |       "_asyncio            bz2                 lxml                shutil\n",
357 |       "_bisect             cProfile            lzma                signal\n",
358 |       "_blake2             calendar            macpath             simplegeneric\n",
359 |       "_bootlocale         cffi                macurl2path         singledispatch\n",
360 |       "_bz2                cgi                 mailbox             singledispatch_helpers\n",
361 |       "_cffi_backend       cgitb               mailcap             sip\n",
362 |       "_codecs             chardet             markupsafe          sipconfig\n",
363 |       "_codecs_cn          chunk               marshal             sipdistutils\n",
364 |       "_codecs_hk          click               math                site\n",
365 |       "_codecs_iso2022     cloudpickle         matplotlib          six\n",
366 |       "_codecs_jp          clyent              mimetypes           skimage\n",
367 |       "_codecs_kr          cmath               mistune             sklearn\n",
368 |       "_codecs_tw          cmd                 mkl                 smtpd\n",
369 |       "_collections        code                mmap                smtplib\n",
370 |       "_collections_abc    codecs              modulefinder        sndhdr\n",
371 |       "_compat_pickle      codeop              mpl_toolkits        snowballstemmer\n",
372 |       "_compression        collections         mpmath              socket\n",
373 |       "_crypt              colorama            msgpack             socketserver\n",
374 |       "_csv                colorsys            multipledispatch    sortedcollections\n",
375 |       "_ctypes             compileall          multiprocessing     sortedcontainers\n",
376 |       "_ctypes_test        concurrent          navigator_updater   sphinx\n",
377 |       "_curses             conda               nbconvert           spwd\n",
378 |       "_curses_panel       conda_env           nbformat            spyder\n",
379 |       "_datetime           configparser        netrc               spyder_breakpoints\n",
380 |       "_decimal            contextlib          networkx            spyder_io_dcm\n",
381 |       "_dummy_thread       contextlib2         nis                 spyder_io_hdf5\n",
382 |       "_elementtree        copy                nltk                spyder_profiler\n",
383 |       "_functools          copyreg             nntplib             spyder_pylint\n",
384 |       "_hashlib            crypt               nose                sqlalchemy\n",
385 |       "_heapq              cryptography        notebook            sqlite3\n",
386 |       "_imp                csv                 ntpath              sre_compile\n",
387 |       "_io                 ctypes              nturl2path          sre_constants\n",
388 |       "_json               curl                numba               sre_parse\n",
389 |       "_license            curses              numbers             ssl\n",
390 |       "_locale             cycler              numexpr             stat\n",
391 |       "_lsprof             cython              numpy               statistics\n",
392 |       "_lzma               cythonmagic         numpydoc            statsmodels\n",
393 |       "_markupbase         cytoolz             odo                 storemagic\n",
394 |       "_md5                dask                olefile             string\n",
395 |       "_multibytecodec     datashape           opcode              stringprep\n",
396 |       "_multiprocessing    datetime            openpyxl            struct\n",
397 |       "_opcode             dateutil            operator            subprocess\n",
398 |       "_operator           dbm                 optparse            sunau\n",
399 |       "_osx_support        decimal             os                  symbol\n",
400 |       "_pickle             decorator           ossaudiodev         sympy\n",
401 |       "_posixsubprocess    difflib             packaging           sympyprinting\n",
402 |       "_pydecimal          dis                 pandas              symtable\n",
403 |       "_pyio               distributed         pandocfilters       sys\n",
404 |       "_pytest             distutils           parser              sysconfig\n",
405 |       "_random             doctest             partd               syslog\n",
406 |       "_sha1               docutils            path                tables\n",
407 |       "_sha256             dummy_threading     pathlib             tabnanny\n",
408 |       "_sha3               easy_install        pathlib2            tarfile\n",
409 |       "_sha512             email               patsy               tblib\n",
410 |       "_signal             encodings           pdb                 telnetlib\n",
411 |       "_sitebuiltins       entrypoints         pep8                tempfile\n",
412 |       "_socket             enum                pexpect             terminado\n",
413 |       "_sqlite3            errno               pickle              termios\n",
414 |       "_sre                et_xmlfile          pickleshare         test_path\n",
415 |       "_ssl                fastcache           pickletools         test_pycosat\n",
416 |       "_stat               faulthandler        pip                 testpath\n",
417 |       "_string             fcntl               pipes               tests\n",
418 |       "_strptime           filecmp             pkg_resources       textwrap\n",
419 |       "_struct             fileinput           pkgutil             this\n",
420 |       "_symtable           flask               platform            threading\n",
421 |       "_sysconfigdata_m_linux_x86_64-linux-gnu flask_cors          plistlib            time\n",
422 |       "_testbuffer         fnmatch             ply                 timeit\n",
423 |       "_testcapi           formatter           poplib              tkinter\n",
424 |       "_testimportmultiple fractions           posix               tlz\n",
425 |       "_testmultiphase     ftplib              posixpath           token\n",
426 |       "_thread             functools           pprint              tokenize\n",
427 |       "_threading_local    gc                  profile             toolz\n",
428 |       "_tkinter            genericpath         prompt_toolkit      tornado\n",
429 |       "_tracemalloc        getopt              pstats              trace\n",
430 |       "_warnings           getpass             psutil              traceback\n",
431 |       "_weakref            gettext             pty                 tracemalloc\n",
432 |       "_weakrefset         gevent              ptyprocess          traitlets\n",
433 |       "_yaml               glob                pwd                 tty\n",
434 |       "abc                 greenlet            py                  turtle\n",
435 |       "aifc                grp                 py_compile          turtledemo\n",
436 |       "alabaster           gzip                pyclbr              types\n",
437 |       "anaconda_navigator  h5py                pycosat             typing\n",
438 |       "anaconda_project    hashlib             pycparser           unicodecsv\n",
439 |       "antigravity         heapdict            pycurl              unicodedata\n",
440 |       "argparse            heapq               pydoc               unittest\n",
441 |       "array               hmac                pydoc_data          urllib\n",
442 |       "asn1crypto          html                pyexpat             uu\n",
443 |       "ast                 html5lib            pyflakes            uuid\n",
444 |       "astroid             http                pygments            venv\n",
445 |       "astropy             idlelib             pylab               warnings\n",
446 |       "asynchat            idna                pylint              wave\n",
447 |       "asyncio             imagesize           pyodbc              wcwidth\n",
448 |       "asyncore            imaplib             pyparsing           weakref\n",
449 |       "atexit              imghdr              pytest              webbrowser\n",
450 |       "audioop             imp                 pytz                werkzeug\n",
451 |       "autoreload          importlib           pywt                wheel\n",
452 |       "babel               inspect             pyximport           widgetsnbextension\n",
453 |       "backports           io                  qtawesome           wrapt\n",
454 |       "base64              ipaddress           qtconsole           wsgiref\n",
455 |       "bdb                 ipykernel           qtpy                xdrlib\n",
456 |       "binascii            ipykernel_launcher  queue               xlrd\n",
457 |       "binhex              ipython_genutils    quopri              xlsxwriter\n",
458 |       "binstar_client      ipywidgets          random              xlwt\n",
459 |       "bisect              isort               re                  xml\n",
460 |       "bitarray            itertools           readline            xmlrpc\n",
461 |       "blaze               itsdangerous        reprlib             xxlimited\n",
462 |       "bleach              jdcal               requests            xxsubtype\n",
463 |       "bokeh               jedi                resource            yaml\n",
464 |       "boto                jinja2              rlcompleter         zict\n",
465 |       "bottleneck          json                rmagic              zipapp\n",
466 |       "brain_builtin_inference jsonschema          rope                zipfile\n",
467 |       "brain_dateutil      jupyter             ruamel_yaml         zipimport\n",
468 |       "brain_gi            jupyter_client      runpy               zlib\n",
469 |       "brain_mechanize     jupyter_console     sched               zmq\n",
470 |       "\n",
471 |       "Enter any module name to get more help.  Or, type \"modules spam\" to search\n",
472 |       "for modules whose name or summary contain the string \"spam\".\n",
473 |       "\n"
474 |      ]
475 |     }
476 |    ],
477 |    "source": [
478 |     "help(\"modules\")"
479 |    ]
480 |   }
481 |  ],
482 |  "metadata": {
483 |   "kernelspec": {
484 |    "display_name": "Python 3",
485 |    "language": "python",
486 |    "name": "python3"
487 |   },
488 |   "language_info": {
489 |    "codemirror_mode": {
490 |     "name": "ipython",
491 |     "version": 3
492 |    },
493 |    "file_extension": ".py",
494 |    "mimetype": "text/x-python",
495 |    "name": "python",
496 |    "nbconvert_exporter": "python",
497 |    "pygments_lexer": "ipython3",
498 |    "version": "3.6.1"
499 |   }
500 |  },
501 |  "nbformat": 4,
502 |  "nbformat_minor": 2
503 | }
504 | 


--------------------------------------------------------------------------------
/Anaconda环境安装以及搭建Python多内核环境.docx:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Kdotm/Python_Series/c686d48797b7266934958b09247aa3ffe783c026/Anaconda环境安装以及搭建Python多内核环境.docx


--------------------------------------------------------------------------------
/Python_PyODPS_HTML_to_PDF.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "## 爬取 PyODPS[latest] 并转换为 PDF\n",
  8 |     "- 爬取主链接\n",
  9 |     "- 根据主链接爬取子连接\n",
 10 |     "- 参考子链接爬取HTML并转换为PDF\n",
 11 |     "- 将所有 PDF 整合为一个PDF\n",
 12 |     "---\n",
 13 |     "- 注 :\n",
 14 |     "    - PyOdps PDF在线最新版本\n",
 15 |     "        - 0.3.12"
 16 |    ]
 17 |   },
 18 |   {
 19 |    "cell_type": "code",
 20 |    "execution_count": 15,
 21 |    "metadata": {
 22 |     "collapsed": true
 23 |    },
 24 |    "outputs": [],
 25 |    "source": [
 26 |     "import re\n",
 27 |     "import pdfkit\n",
 28 |     "import pandas as pd\n",
 29 |     "from urllib import urlopen\n",
 30 |     "from bs4 import BeautifulSoup\n",
 31 |     "\n",
 32 |     "# 设置 pandas 显示参数\n",
 33 |     "pd.set_option('display.width',200)\n",
 34 |     "pd.set_option('display.max_rows',1000)\n",
 35 |     "pd.set_option('display.max_columns',50)\n",
 36 |     "pd.set_option('display.max_colwidth',500)"
 37 |    ]
 38 |   },
 39 |   {
 40 |    "cell_type": "markdown",
 41 |    "metadata": {},
 42 |    "source": [
 43 |     "### 爬取主链接\n",
 44 |     "#### 爬取PyODPS Docs主页面"
 45 |    ]
 46 |   },
 47 |   {
 48 |    "cell_type": "code",
 49 |    "execution_count": 9,
 50 |    "metadata": {
 51 |     "collapsed": true
 52 |    },
 53 |    "outputs": [],
 54 |    "source": [
 55 |     "url='http://pyodps.readthedocs.io/zh_CN/latest/index.html'\n",
 56 |     "html=urlopen(url).read().decode('utf8')\n",
 57 |     "soup=BeautifulSoup(html,'lxml')"
 58 |    ]
 59 |   },
 60 |   {
 61 |    "cell_type": "markdown",
 62 |    "metadata": {},
 63 |    "source": [
 64 |     "#### 取值最新文档首页 API及标题"
 65 |    ]
 66 |   },
 67 |   {
 68 |    "cell_type": "code",
 69 |    "execution_count": 10,
 70 |    "metadata": {
 71 |     "collapsed": true
 72 |    },
 73 |    "outputs": [],
 74 |    "source": [
 75 |     "# 主链接 (API)\n",
 76 |     "api=soup.find(name='link', attrs={'rel':'canonical'}).get('href')\n",
 77 |     "# 获取文档标题\n",
 78 |     "title=soup.find('link',attrs={\"href\":\"#\",\"rel\":\"top\"}).get('title').replace(' ','_')\n",
 79 |     "\n",
 80 |     "# 获取首页超链接 (href)\n",
 81 |     "hrefs=[]\n",
 82 |     "div_s=soup.find_all(name='div',attrs={'aria-label':'main navigation','role':'navigation'})[0]\n",
 83 |     "for tag_a in div_s.find_all(name='a',attrs={'class':'reference internal'}):\n",
 84 |     "    content_name=tag_a.get_text()\n",
 85 |     "    url=api+tag_a.get('href')\n",
 86 |     "    hrefs.append([content_name,url])"
 87 |    ]
 88 |   },
 89 |   {
 90 |    "cell_type": "markdown",
 91 |    "metadata": {},
 92 |    "source": [
 93 |     "#### 美化 DataFrame 显示效果函数"
 94 |    ]
 95 |   },
 96 |   {
 97 |    "cell_type": "code",
 98 |    "execution_count": 20,
 99 |    "metadata": {
100 |     "collapsed": true
101 |    },
102 |    "outputs": [],
103 |    "source": [
104 |     "'''\n",
105 |     "设置悬停效果\n",
106 |     "'''\n",
107 |     "def hover(hover_color=\"#ffff99\"):\n",
108 |     "    return dict(selector=\"tr:hover\",\n",
109 |     "                props=[(\"background-color\", \"%s\" % hover_color)])\n",
110 |     "'''\n",
111 |     "美化DataFrame显示效果\n",
112 |     "'''\n",
113 |     "def display_prettify(df):\n",
114 |     "    from IPython.display import HTML\n",
115 |     "\n",
116 |     "    styles = [\n",
117 |     "        hover(),\n",
118 |     "        dict(selector=\"th\", props=[(\"font-size\", \"100%\"),\n",
119 |     "                                   (\"text-align\", \"center\")]),\n",
120 |     "        dict(selector=\"td\", props=[(\"text-align\", \"left\")]),\n",
121 |     "        dict(selector=\"caption\", props=[(\"caption-side\", \"left\")])\n",
122 |     "    ]\n",
123 |     "    return df.style.set_table_styles(styles).set_caption(\"Hover to highlight.\")"
124 |    ]
125 |   },
126 |   {
127 |    "cell_type": "markdown",
128 |    "metadata": {},
129 |    "source": [
130 |     "#### 首页超连接(href)打印显示"
131 |    ]
132 |   },
133 |   {
134 |    "cell_type": "code",
135 |    "execution_count": 13,
136 |    "metadata": {},
137 |    "outputs": [
138 |     {
139 |      "data": {
140 |       "text/html": [
141 |        "<style  type=\"text/css\" >\n",
142 |        "    #T_d14342c0_08c8_11e8_97b2_000c29730229 tr:hover {\n",
143 |        "          background-color: #ffff99;\n",
144 |        "    }    #T_d14342c0_08c8_11e8_97b2_000c29730229 th {\n",
145 |        "          font-size: 100%;\n",
146 |        "          text-align: center;\n",
147 |        "    }    #T_d14342c0_08c8_11e8_97b2_000c29730229 td {\n",
148 |        "          text-align: left;\n",
149 |        "    }    #T_d14342c0_08c8_11e8_97b2_000c29730229 caption {\n",
150 |        "          caption-side: left;\n",
151 |        "    }</style>  \n",
152 |        "<table id=\"T_d14342c0_08c8_11e8_97b2_000c29730229\" ><caption>Hover to highlight.</caption> \n",
153 |        "<thead>    <tr> \n",
154 |        "        <th class=\"blank level0\" ></th> \n",
155 |        "        <th class=\"col_heading level0 col0\" >content_name</th> \n",
156 |        "        <th class=\"col_heading level0 col1\" >href</th> \n",
157 |        "    </tr></thead> \n",
158 |        "<tbody>    <tr> \n",
159 |        "        <th id=\"T_d14342c0_08c8_11e8_97b2_000c29730229\" class=\"row_heading level0 row0\" >0</th> \n",
160 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row0_col0\" class=\"data row0 col0\" >安装指南</td> \n",
161 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row0_col1\" class=\"data row0 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/installation-pub-zh.html</td> \n",
162 |        "    </tr>    <tr> \n",
163 |        "        <th id=\"T_d14342c0_08c8_11e8_97b2_000c29730229\" class=\"row_heading level0 row1\" >1</th> \n",
164 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row1_col0\" class=\"data row1 col0\" >基本操作</td> \n",
165 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row1_col1\" class=\"data row1 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/base-zh.html</td> \n",
166 |        "    </tr>    <tr> \n",
167 |        "        <th id=\"T_d14342c0_08c8_11e8_97b2_000c29730229\" class=\"row_heading level0 row2\" >2</th> \n",
168 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row2_col0\" class=\"data row2 col0\" >DataFrame</td> \n",
169 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row2_col1\" class=\"data row2 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/df-zh.html</td> \n",
170 |        "    </tr>    <tr> \n",
171 |        "        <th id=\"T_d14342c0_08c8_11e8_97b2_000c29730229\" class=\"row_heading level0 row3\" >3</th> \n",
172 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row3_col0\" class=\"data row3 col0\" >机器学习</td> \n",
173 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row3_col1\" class=\"data row3 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/ml-zh.html</td> \n",
174 |        "    </tr>    <tr> \n",
175 |        "        <th id=\"T_d14342c0_08c8_11e8_97b2_000c29730229\" class=\"row_heading level0 row4\" >4</th> \n",
176 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row4_col0\" class=\"data row4 col0\" >交互体验增强</td> \n",
177 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row4_col1\" class=\"data row4 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/interactive-zh.html</td> \n",
178 |        "    </tr>    <tr> \n",
179 |        "        <th id=\"T_d14342c0_08c8_11e8_97b2_000c29730229\" class=\"row_heading level0 row5\" >5</th> \n",
180 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row5_col0\" class=\"data row5 col0\" >配置选项</td> \n",
181 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row5_col1\" class=\"data row5 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/options-zh.html</td> \n",
182 |        "    </tr>    <tr> \n",
183 |        "        <th id=\"T_d14342c0_08c8_11e8_97b2_000c29730229\" class=\"row_heading level0 row6\" >6</th> \n",
184 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row6_col0\" class=\"data row6 col0\" >API Reference</td> \n",
185 |        "        <td id=\"T_d14342c0_08c8_11e8_97b2_000c29730229row6_col1\" class=\"data row6 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/api.html</td> \n",
186 |        "    </tr></tbody> \n",
187 |        "</table> "
188 |       ],
189 |       "text/plain": [
190 |        "<pandas.io.formats.style.Styler at 0x7fc950324e10>"
191 |       ]
192 |      },
193 |      "execution_count": 13,
194 |      "metadata": {},
195 |      "output_type": "execute_result"
196 |     }
197 |    ],
198 |    "source": [
199 |     "df=pd.DataFrame(hrefs, columns=['content_name','href'])\n",
200 |     "\n",
201 |     "display_prettify(df)"
202 |    ]
203 |   },
204 |   {
205 |    "cell_type": "markdown",
206 |    "metadata": {},
207 |    "source": [
208 |     "### 根据主链接爬取子连接"
209 |    ]
210 |   },
211 |   {
212 |    "cell_type": "code",
213 |    "execution_count": null,
214 |    "metadata": {
215 |     "collapsed": true
216 |    },
217 |    "outputs": [],
218 |    "source": [
219 |     "hrefs_2=[] # 有序列表，存储主、子链接并与文档目录层次结构保持一致性\n",
220 |     "\n",
221 |     "for name,url in hrefs:\n",
222 |     "    if url not in [hf[1] for hf in hrefs_2]: # href 不在 hrefs_2中，则追加\n",
223 |     "        hrefs_2.append([name,url])\n",
224 |     "    t_html=urlopen(url).read().decode('utf8')\n",
225 |     "    \n",
226 |     "    # 根据正则表达式 查找当前目录主题\n",
227 |     "    f_re='<a class=\"current reference internal\".*?</a><ul>(.*?)</ul>'\n",
228 |     "    if len(re.findall(f_re, t_html, re.I|re.S|re.M)) !=0 :\n",
229 |     "        target_s = re.findall(f_re, t_html, re.I|re.S|re.M)[0]\n",
230 |     "\n",
231 |     "        # 根据正则表达式 获取当前子主题链接\n",
232 |     "        t_re='<a class=\"reference internal\" href=\"(.*?)\">(.*?)</a>'\n",
233 |     "        for href,name in re.findall(t_re, target_s, re.I|re.S|re.M):\n",
234 |     "            if href.strip().endswith('.html'):\n",
235 |     "                hrefs_2.append([name,api+href])"
236 |    ]
237 |   },
238 |   {
239 |    "cell_type": "code",
240 |    "execution_count": 22,
241 |    "metadata": {},
242 |    "outputs": [
243 |     {
244 |      "data": {
245 |       "text/html": [
246 |        "<style  type=\"text/css\" >\n",
247 |        "    #T_3c373dac_08ce_11e8_97b2_000c29730229 tr:hover {\n",
248 |        "          background-color: #ffff99;\n",
249 |        "    }    #T_3c373dac_08ce_11e8_97b2_000c29730229 th {\n",
250 |        "          font-size: 100%;\n",
251 |        "          text-align: center;\n",
252 |        "    }    #T_3c373dac_08ce_11e8_97b2_000c29730229 td {\n",
253 |        "          text-align: left;\n",
254 |        "    }    #T_3c373dac_08ce_11e8_97b2_000c29730229 caption {\n",
255 |        "          caption-side: left;\n",
256 |        "    }</style>  \n",
257 |        "<table id=\"T_3c373dac_08ce_11e8_97b2_000c29730229\" ><caption>Hover to highlight.</caption> \n",
258 |        "<thead>    <tr> \n",
259 |        "        <th class=\"blank level0\" ></th> \n",
260 |        "        <th class=\"col_heading level0 col0\" >0</th> \n",
261 |        "        <th class=\"col_heading level0 col1\" >1</th> \n",
262 |        "    </tr></thead> \n",
263 |        "<tbody>    <tr> \n",
264 |        "        <th id=\"T_3c373dac_08ce_11e8_97b2_000c29730229\" class=\"row_heading level0 row0\" >0</th> \n",
265 |        "        <td id=\"T_3c373dac_08ce_11e8_97b2_000c29730229row0_col0\" class=\"data row0 col0\" >安装指南</td> \n",
266 |        "        <td id=\"T_3c373dac_08ce_11e8_97b2_000c29730229row0_col1\" class=\"data row0 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/installation-pub-zh.html</td> \n",
267 |        "    </tr>    <tr> \n",
268 |        "        <th id=\"T_3c373dac_08ce_11e8_97b2_000c29730229\" class=\"row_heading level0 row1\" >1</th> \n",
269 |        "        <td id=\"T_3c373dac_08ce_11e8_97b2_000c29730229row1_col0\" class=\"data row1 col0\" >基本操作</td> \n",
270 |        "        <td id=\"T_3c373dac_08ce_11e8_97b2_000c29730229row1_col1\" class=\"data row1 col1\" >http://pyodps.readthedocs.io/zh_CN/latest/base-zh.html</td> \n",
271 |        "    </tr></tbody> \n",
272 |        "</table> "
273 |       ],
274 |       "text/plain": [
275 |        "<pandas.io.formats.style.Styler at 0x7fc94dab0ed0>"
276 |       ]
277 |      },
278 |      "execution_count": 22,
279 |      "metadata": {},
280 |      "output_type": "execute_result"
281 |     }
282 |    ],
283 |    "source": [
284 |     "display_prettify(pd.DataFrame(hrefs_2))"
285 |    ]
286 |   },
287 |   {
288 |    "cell_type": "markdown",
289 |    "metadata": {},
290 |    "source": [
291 |     "#### 显示PyODPS 所有链接"
292 |    ]
293 |   },
294 |   {
295 |    "cell_type": "code",
296 |    "execution_count": 105,
297 |    "metadata": {},
298 |    "outputs": [
299 |     {
300 |      "data": {
301 |       "text/html": [
302 |        "<div>\n",
303 |        "<style>\n",
304 |        "    .dataframe thead tr:only-child th {\n",
305 |        "        text-align: right;\n",
306 |        "    }\n",
307 |        "\n",
308 |        "    .dataframe thead th {\n",
309 |        "        text-align: left;\n",
310 |        "    }\n",
311 |        "\n",
312 |        "    .dataframe tbody tr th {\n",
313 |        "        vertical-align: top;\n",
314 |        "    }\n",
315 |        "</style>\n",
316 |        "<table border=\"1\" class=\"dataframe\">\n",
317 |        "  <thead>\n",
318 |        "    <tr style=\"text-align: right;\">\n",
319 |        "      <th></th>\n",
320 |        "      <th>0</th>\n",
321 |        "      <th>1</th>\n",
322 |        "    </tr>\n",
323 |        "  </thead>\n",
324 |        "  <tbody>\n",
325 |        "    <tr>\n",
326 |        "      <th>0</th>\n",
327 |        "      <td>安装指南</td>\n",
328 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/installation-pub-zh.html</td>\n",
329 |        "    </tr>\n",
330 |        "    <tr>\n",
331 |        "      <th>1</th>\n",
332 |        "      <td>基本操作</td>\n",
333 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/base-zh.html</td>\n",
334 |        "    </tr>\n",
335 |        "    <tr>\n",
336 |        "      <th>2</th>\n",
337 |        "      <td>项目空间</td>\n",
338 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/base-projects-zh.html</td>\n",
339 |        "    </tr>\n",
340 |        "    <tr>\n",
341 |        "      <th>3</th>\n",
342 |        "      <td>表</td>\n",
343 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/base-tables-zh.html</td>\n",
344 |        "    </tr>\n",
345 |        "    <tr>\n",
346 |        "      <th>4</th>\n",
347 |        "      <td>SQL</td>\n",
348 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/base-sql-zh.html</td>\n",
349 |        "    </tr>\n",
350 |        "    <tr>\n",
351 |        "      <th>5</th>\n",
352 |        "      <td>任务实例</td>\n",
353 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/base-instances-zh.html</td>\n",
354 |        "    </tr>\n",
355 |        "    <tr>\n",
356 |        "      <th>6</th>\n",
357 |        "      <td>资源</td>\n",
358 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/base-resources-zh.html</td>\n",
359 |        "    </tr>\n",
360 |        "    <tr>\n",
361 |        "      <th>7</th>\n",
362 |        "      <td>函数</td>\n",
363 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/base-functions-zh.html</td>\n",
364 |        "    </tr>\n",
365 |        "    <tr>\n",
366 |        "      <th>8</th>\n",
367 |        "      <td>模型</td>\n",
368 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/base-models-zh.html</td>\n",
369 |        "    </tr>\n",
370 |        "    <tr>\n",
371 |        "      <th>9</th>\n",
372 |        "      <td>DataFrame</td>\n",
373 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-zh.html</td>\n",
374 |        "    </tr>\n",
375 |        "    <tr>\n",
376 |        "      <th>10</th>\n",
377 |        "      <td>快速开始</td>\n",
378 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-quickstart-zh.html</td>\n",
379 |        "    </tr>\n",
380 |        "    <tr>\n",
381 |        "      <th>11</th>\n",
382 |        "      <td>基本概念</td>\n",
383 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-basic-zh.html</td>\n",
384 |        "    </tr>\n",
385 |        "    <tr>\n",
386 |        "      <th>12</th>\n",
387 |        "      <td>列运算</td>\n",
388 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-element-zh.html</td>\n",
389 |        "    </tr>\n",
390 |        "    <tr>\n",
391 |        "      <th>13</th>\n",
392 |        "      <td>聚合操作</td>\n",
393 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-agg-zh.html</td>\n",
394 |        "    </tr>\n",
395 |        "    <tr>\n",
396 |        "      <th>14</th>\n",
397 |        "      <td>排序、去重、采样、数据变换</td>\n",
398 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-sort-distinct-apply-zh.html</td>\n",
399 |        "    </tr>\n",
400 |        "    <tr>\n",
401 |        "      <th>15</th>\n",
402 |        "      <td>数据合并</td>\n",
403 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-merge-zh.html</td>\n",
404 |        "    </tr>\n",
405 |        "    <tr>\n",
406 |        "      <th>16</th>\n",
407 |        "      <td>窗口函数</td>\n",
408 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-window-zh.html</td>\n",
409 |        "    </tr>\n",
410 |        "    <tr>\n",
411 |        "      <th>17</th>\n",
412 |        "      <td>绘图</td>\n",
413 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-plot-zh.html</td>\n",
414 |        "    </tr>\n",
415 |        "    <tr>\n",
416 |        "      <th>18</th>\n",
417 |        "      <td>调试指南</td>\n",
418 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/df-debug-instruction-zh.html</td>\n",
419 |        "    </tr>\n",
420 |        "    <tr>\n",
421 |        "      <th>19</th>\n",
422 |        "      <td>机器学习</td>\n",
423 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/ml-zh.html</td>\n",
424 |        "    </tr>\n",
425 |        "    <tr>\n",
426 |        "      <th>20</th>\n",
427 |        "      <td>快速开始</td>\n",
428 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/ml-quickstart-zh.html</td>\n",
429 |        "    </tr>\n",
430 |        "    <tr>\n",
431 |        "      <th>21</th>\n",
432 |        "      <td>基本概念</td>\n",
433 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/ml-basic-zh.html</td>\n",
434 |        "    </tr>\n",
435 |        "    <tr>\n",
436 |        "      <th>22</th>\n",
437 |        "      <td>调用算法</td>\n",
438 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/ml-algo-pub-zh.html</td>\n",
439 |        "    </tr>\n",
440 |        "    <tr>\n",
441 |        "      <th>23</th>\n",
442 |        "      <td>结果评估</td>\n",
443 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/ml-assess-zh.html</td>\n",
444 |        "    </tr>\n",
445 |        "    <tr>\n",
446 |        "      <th>24</th>\n",
447 |        "      <td>交互体验增强</td>\n",
448 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/interactive-zh.html</td>\n",
449 |        "    </tr>\n",
450 |        "    <tr>\n",
451 |        "      <th>25</th>\n",
452 |        "      <td>配置选项</td>\n",
453 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/options-zh.html</td>\n",
454 |        "    </tr>\n",
455 |        "    <tr>\n",
456 |        "      <th>26</th>\n",
457 |        "      <td>API Reference</td>\n",
458 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/api.html</td>\n",
459 |        "    </tr>\n",
460 |        "    <tr>\n",
461 |        "      <th>27</th>\n",
462 |        "      <td>Definitions</td>\n",
463 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/api-def.html</td>\n",
464 |        "    </tr>\n",
465 |        "    <tr>\n",
466 |        "      <th>28</th>\n",
467 |        "      <td>DataFrame Reference</td>\n",
468 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/api-df.html</td>\n",
469 |        "    </tr>\n",
470 |        "    <tr>\n",
471 |        "      <th>29</th>\n",
472 |        "      <td>ML References</td>\n",
473 |        "      <td>http://pyodps.readthedocs.io/zh_CN/latest/api-ml.html</td>\n",
474 |        "    </tr>\n",
475 |        "  </tbody>\n",
476 |        "</table>\n",
477 |        "</div>"
478 |       ],
479 |       "text/plain": [
480 |        "                      0                                                                         1\n",
481 |        "0                  安装指南        http://pyodps.readthedocs.io/zh_CN/latest/installation-pub-zh.html\n",
482 |        "1                  基本操作                    http://pyodps.readthedocs.io/zh_CN/latest/base-zh.html\n",
483 |        "2                  项目空间           http://pyodps.readthedocs.io/zh_CN/latest/base-projects-zh.html\n",
484 |        "3                     表             http://pyodps.readthedocs.io/zh_CN/latest/base-tables-zh.html\n",
485 |        "4                   SQL                http://pyodps.readthedocs.io/zh_CN/latest/base-sql-zh.html\n",
486 |        "5                  任务实例          http://pyodps.readthedocs.io/zh_CN/latest/base-instances-zh.html\n",
487 |        "6                    资源          http://pyodps.readthedocs.io/zh_CN/latest/base-resources-zh.html\n",
488 |        "7                    函数          http://pyodps.readthedocs.io/zh_CN/latest/base-functions-zh.html\n",
489 |        "8                    模型             http://pyodps.readthedocs.io/zh_CN/latest/base-models-zh.html\n",
490 |        "9             DataFrame                      http://pyodps.readthedocs.io/zh_CN/latest/df-zh.html\n",
491 |        "10                 快速开始           http://pyodps.readthedocs.io/zh_CN/latest/df-quickstart-zh.html\n",
492 |        "11                 基本概念                http://pyodps.readthedocs.io/zh_CN/latest/df-basic-zh.html\n",
493 |        "12                  列运算              http://pyodps.readthedocs.io/zh_CN/latest/df-element-zh.html\n",
494 |        "13                 聚合操作                  http://pyodps.readthedocs.io/zh_CN/latest/df-agg-zh.html\n",
495 |        "14        排序、去重、采样、数据变换  http://pyodps.readthedocs.io/zh_CN/latest/df-sort-distinct-apply-zh.html\n",
496 |        "15                 数据合并                http://pyodps.readthedocs.io/zh_CN/latest/df-merge-zh.html\n",
497 |        "16                 窗口函数               http://pyodps.readthedocs.io/zh_CN/latest/df-window-zh.html\n",
498 |        "17                   绘图                 http://pyodps.readthedocs.io/zh_CN/latest/df-plot-zh.html\n",
499 |        "18                 调试指南    http://pyodps.readthedocs.io/zh_CN/latest/df-debug-instruction-zh.html\n",
500 |        "19                 机器学习                      http://pyodps.readthedocs.io/zh_CN/latest/ml-zh.html\n",
501 |        "20                 快速开始           http://pyodps.readthedocs.io/zh_CN/latest/ml-quickstart-zh.html\n",
502 |        "21                 基本概念                http://pyodps.readthedocs.io/zh_CN/latest/ml-basic-zh.html\n",
503 |        "22                 调用算法             http://pyodps.readthedocs.io/zh_CN/latest/ml-algo-pub-zh.html\n",
504 |        "23                 结果评估               http://pyodps.readthedocs.io/zh_CN/latest/ml-assess-zh.html\n",
505 |        "24               交互体验增强             http://pyodps.readthedocs.io/zh_CN/latest/interactive-zh.html\n",
506 |        "25                 配置选项                 http://pyodps.readthedocs.io/zh_CN/latest/options-zh.html\n",
507 |        "26        API Reference                        http://pyodps.readthedocs.io/zh_CN/latest/api.html\n",
508 |        "27          Definitions                    http://pyodps.readthedocs.io/zh_CN/latest/api-def.html\n",
509 |        "28  DataFrame Reference                     http://pyodps.readthedocs.io/zh_CN/latest/api-df.html\n",
510 |        "29        ML References                     http://pyodps.readthedocs.io/zh_CN/latest/api-ml.html"
511 |       ]
512 |      },
513 |      "execution_count": 105,
514 |      "metadata": {},
515 |      "output_type": "execute_result"
516 |     }
517 |    ],
518 |    "source": [
519 |     "pd.DataFrame(hrefs_2)"
520 |    ]
521 |   },
522 |   {
523 |    "cell_type": "markdown",
524 |    "metadata": {
525 |     "code_folding": []
526 |    },
527 |    "source": [
528 |     "### 参考子链接爬取HTML并转换为PDF"
529 |    ]
530 |   },
531 |   {
532 |    "cell_type": "code",
533 |    "execution_count": 24,
534 |    "metadata": {},
535 |    "outputs": [
536 |     {
537 |      "name": "stdout",
538 |      "output_type": "stream",
539 |      "text": [
540 |       "Loading pages (1/6)\n",
541 |       "QFont::setPixelSize: Pixel size <= 0 (0)                     ] 35%\n",
542 |       "Counting pages (2/6)                                               \n",
543 |       "Resolving links (4/6)                                                       \n",
544 |       "Loading headers and footers (5/6)                                           \n",
545 |       "Printing pages (6/6)\n",
546 |       "Done                                                                      \n",
547 |       "Loading pages (1/6)\n",
548 |       "QFont::setPixelSize: Pixel size <= 0 (0)                     ] 26%\n",
549 |       "Counting pages (2/6)                                               \n",
550 |       "Resolving links (4/6)                                                       \n",
551 |       "Loading headers and footers (5/6)                                           \n",
552 |       "Printing pages (6/6)\n",
553 |       "Done                                                                      \n"
554 |      ]
555 |     }
556 |    ],
557 |    "source": [
558 |     "for name,href in hrefs_2:\n",
559 |     "    pdfkit.from_url(href,'./tmp/'+name+'.pdf')"
560 |    ]
561 |   },
562 |   {
563 |    "cell_type": "markdown",
564 |    "metadata": {},
565 |    "source": [
566 |     "### 整合所有 PDF"
567 |    ]
568 |   },
569 |   {
570 |    "cell_type": "code",
571 |    "execution_count": 114,
572 |    "metadata": {
573 |     "collapsed": true
574 |    },
575 |    "outputs": [],
576 |    "source": [
577 |     "from PyPDF2 import PdfFileMerger\n",
578 |     "\n",
579 |     "# 创建 PdfFileMerger 对象，合并PDFs\n",
580 |     "merger = PdfFileMerger()\n",
581 |     "for name, url in hrefs_2:\n",
582 |     "    t_input = open('./tmp/'+name+'.pdf', 'rb')\n",
583 |     "    merger.append(t_input)\n",
584 |     "\n",
585 |     "# 流输出\n",
586 |     "output = open(title+\".pdf\", \"wb\")\n",
587 |     "merger.write(output)\n",
588 |     "\n",
589 |     "# 关闭文件流\n",
590 |     "output.close()\n",
591 |     "merger.close()"
592 |    ]
593 |   }
594 |  ],
595 |  "metadata": {
596 |   "kernelspec": {
597 |    "display_name": "Python 2",
598 |    "language": "python",
599 |    "name": "python2"
600 |   },
601 |   "language_info": {
602 |    "codemirror_mode": {
603 |     "name": "ipython",
604 |     "version": 2
605 |    },
606 |    "file_extension": ".py",
607 |    "mimetype": "text/x-python",
608 |    "name": "python",
609 |    "nbconvert_exporter": "python",
610 |    "pygments_lexer": "ipython2",
611 |    "version": "2.7.13"
612 |   },
613 |   "toc": {
614 |    "nav_menu": {},
615 |    "number_sections": true,
616 |    "sideBar": true,
617 |    "skip_h1_title": false,
618 |    "toc_cell": false,
619 |    "toc_position": {
620 |     "height": "454px",
621 |     "left": "0px",
622 |     "right": "745.925px",
623 |     "top": "107px",
624 |     "width": "290px"
625 |    },
626 |    "toc_section_display": "block",
627 |    "toc_window_display": true
628 |   }
629 |  },
630 |  "nbformat": 4,
631 |  "nbformat_minor": 2
632 | }
633 | 


--------------------------------------------------------------------------------
/Python操作Mysql实例教程手册_代码.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "metadata": {},
   6 |    "source": [
   7 |     "#### 设置样式显示效果"
   8 |    ]
   9 |   },
  10 |   {
  11 |    "cell_type": "code",
  12 |    "execution_count": 15,
  13 |    "metadata": {
  14 |     "collapsed": true
  15 |    },
  16 |    "outputs": [],
  17 |    "source": [
  18 |     "\n",
  19 |     "'''\n",
  20 |     "设置悬停效果\n",
  21 |     "'''\n",
  22 |     "def hover(hover_color=\"#ffff99\"):\n",
  23 |     "    return dict(selector=\"tr:hover\",\n",
  24 |     "                props=[(\"background-color\", \"%s\" % hover_color)])\n",
  25 |     "'''\n",
  26 |     "美化DataFrame显示效果\n",
  27 |     "'''\n",
  28 |     "def display_prettify(df):\n",
  29 |     "    from IPython.display import HTML\n",
  30 |     "\n",
  31 |     "    styles = [\n",
  32 |     "        hover(),\n",
  33 |     "        dict(selector=\"th\", props=[(\"font-size\", \"100%\"),\n",
  34 |     "                                   (\"text-align\", \"center\")]),\n",
  35 |     "        dict(selector=\"td\", props=[(\"text-align\", \"left\")]),\n",
  36 |     "        dict(selector=\"caption\", props=[(\"caption-side\", \"left\")])\n",
  37 |     "    ]\n",
  38 |     "    return df.style.set_table_styles(styles).set_caption(\"Hover to highlight.\")"
  39 |    ]
  40 |   },
  41 |   {
  42 |    "cell_type": "markdown",
  43 |    "metadata": {},
  44 |    "source": [
  45 |     "###  取得 MariaDB 版本"
  46 |    ]
  47 |   },
  48 |   {
  49 |    "cell_type": "code",
  50 |    "execution_count": 18,
  51 |    "metadata": {},
  52 |    "outputs": [],
  53 |    "source": [
  54 |     "ip,user,pwd,dnname,port='192.168.182.131','root','root','mysql',3306\n",
  55 |     "\n",
  56 |     "import MySQLdb as mdb\n",
  57 |     "\n",
  58 |     "conn = None\n",
  59 |     "try:\n",
  60 |     "    '''\n",
  61 |     "    1 connect mysql\n",
  62 |     "        type : MySQLdb.connections.Connection\n",
  63 |     "        func : connect(ip,user,password,dbname)\n",
  64 |     "    '''\n",
  65 |     "    conn = mdb.connect(ip,user,pwd,dnname,port)\n",
  66 |     "    cursor = conn.cursor()\n",
  67 |     "    \n",
  68 |     "    '''\n",
  69 |     "    2 fetchone\n",
  70 |     "       单条结果，返回单个元组 \n",
  71 |     "    '''\n",
  72 |     "    cursor.execute(\"SELECT VERSION();\")  # 执行查询\n",
  73 |     "    row = cursor.fetchone()\n",
  74 |     "    \n",
  75 |     "    '''\n",
  76 |     "    3 fetchall\n",
  77 |     "       所有结果，返回二维元组 \n",
  78 |     "    '''\n",
  79 |     "    cursor.execute(\"select * from user;\")  # 执行查询\n",
  80 |     "    rows = cursor.fetchall()\n",
  81 |     "finally:\n",
  82 |     "    if conn:\n",
  83 |     "        conn.close() # 关闭连接\n",
  84 |     "        cursor.close()"
  85 |    ]
  86 |   },
  87 |   {
  88 |    "cell_type": "code",
  89 |    "execution_count": 20,
  90 |    "metadata": {
  91 |     "scrolled": false
  92 |    },
  93 |    "outputs": [
  94 |     {
  95 |      "data": {
  96 |       "text/html": [
  97 |        "<style  type=\"text/css\" >\n",
  98 |        "    #T_4a8bdd7e_0ade_11e8_9727_000c29730229 tr:hover {\n",
  99 |        "          background-color: #ffff99;\n",
 100 |        "    }    #T_4a8bdd7e_0ade_11e8_9727_000c29730229 th {\n",
 101 |        "          font-size: 100%;\n",
 102 |        "          text-align: center;\n",
 103 |        "    }    #T_4a8bdd7e_0ade_11e8_9727_000c29730229 td {\n",
 104 |        "          text-align: left;\n",
 105 |        "    }    #T_4a8bdd7e_0ade_11e8_9727_000c29730229 caption {\n",
 106 |        "          caption-side: left;\n",
 107 |        "    }</style>  \n",
 108 |        "<table id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229\" ><caption>Hover to highlight.</caption> \n",
 109 |        "<thead>    <tr> \n",
 110 |        "        <th class=\"blank level0\" ></th> \n",
 111 |        "        <th class=\"col_heading level0 col0\" >0</th> \n",
 112 |        "        <th class=\"col_heading level0 col1\" >1</th> \n",
 113 |        "        <th class=\"col_heading level0 col2\" >2</th> \n",
 114 |        "        <th class=\"col_heading level0 col3\" >3</th> \n",
 115 |        "        <th class=\"col_heading level0 col4\" >4</th> \n",
 116 |        "        <th class=\"col_heading level0 col5\" >5</th> \n",
 117 |        "        <th class=\"col_heading level0 col6\" >6</th> \n",
 118 |        "        <th class=\"col_heading level0 col7\" >7</th> \n",
 119 |        "        <th class=\"col_heading level0 col8\" >8</th> \n",
 120 |        "        <th class=\"col_heading level0 col9\" >9</th> \n",
 121 |        "        <th class=\"col_heading level0 col10\" >10</th> \n",
 122 |        "        <th class=\"col_heading level0 col11\" >11</th> \n",
 123 |        "        <th class=\"col_heading level0 col12\" >12</th> \n",
 124 |        "        <th class=\"col_heading level0 col13\" >13</th> \n",
 125 |        "        <th class=\"col_heading level0 col14\" >14</th> \n",
 126 |        "        <th class=\"col_heading level0 col15\" >15</th> \n",
 127 |        "        <th class=\"col_heading level0 col16\" >16</th> \n",
 128 |        "        <th class=\"col_heading level0 col17\" >17</th> \n",
 129 |        "        <th class=\"col_heading level0 col18\" >18</th> \n",
 130 |        "        <th class=\"col_heading level0 col19\" >19</th> \n",
 131 |        "        <th class=\"col_heading level0 col20\" >20</th> \n",
 132 |        "        <th class=\"col_heading level0 col21\" >21</th> \n",
 133 |        "        <th class=\"col_heading level0 col22\" >22</th> \n",
 134 |        "        <th class=\"col_heading level0 col23\" >23</th> \n",
 135 |        "        <th class=\"col_heading level0 col24\" >24</th> \n",
 136 |        "        <th class=\"col_heading level0 col25\" >25</th> \n",
 137 |        "        <th class=\"col_heading level0 col26\" >26</th> \n",
 138 |        "        <th class=\"col_heading level0 col27\" >27</th> \n",
 139 |        "        <th class=\"col_heading level0 col28\" >28</th> \n",
 140 |        "        <th class=\"col_heading level0 col29\" >29</th> \n",
 141 |        "        <th class=\"col_heading level0 col30\" >30</th> \n",
 142 |        "        <th class=\"col_heading level0 col31\" >31</th> \n",
 143 |        "        <th class=\"col_heading level0 col32\" >32</th> \n",
 144 |        "        <th class=\"col_heading level0 col33\" >33</th> \n",
 145 |        "        <th class=\"col_heading level0 col34\" >34</th> \n",
 146 |        "        <th class=\"col_heading level0 col35\" >35</th> \n",
 147 |        "        <th class=\"col_heading level0 col36\" >36</th> \n",
 148 |        "        <th class=\"col_heading level0 col37\" >37</th> \n",
 149 |        "        <th class=\"col_heading level0 col38\" >38</th> \n",
 150 |        "        <th class=\"col_heading level0 col39\" >39</th> \n",
 151 |        "        <th class=\"col_heading level0 col40\" >40</th> \n",
 152 |        "        <th class=\"col_heading level0 col41\" >41</th> \n",
 153 |        "        <th class=\"col_heading level0 col42\" >42</th> \n",
 154 |        "        <th class=\"col_heading level0 col43\" >43</th> \n",
 155 |        "        <th class=\"col_heading level0 col44\" >44</th> \n",
 156 |        "        <th class=\"col_heading level0 col45\" >45</th> \n",
 157 |        "    </tr></thead> \n",
 158 |        "<tbody>    <tr> \n",
 159 |        "        <th id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229\" class=\"row_heading level0 row0\" >0</th> \n",
 160 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col0\" class=\"data row0 col0\" >localhost</td> \n",
 161 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col1\" class=\"data row0 col1\" >root</td> \n",
 162 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col2\" class=\"data row0 col2\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 163 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col3\" class=\"data row0 col3\" >Y</td> \n",
 164 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col4\" class=\"data row0 col4\" >Y</td> \n",
 165 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col5\" class=\"data row0 col5\" >Y</td> \n",
 166 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col6\" class=\"data row0 col6\" >Y</td> \n",
 167 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col7\" class=\"data row0 col7\" >Y</td> \n",
 168 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col8\" class=\"data row0 col8\" >Y</td> \n",
 169 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col9\" class=\"data row0 col9\" >Y</td> \n",
 170 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col10\" class=\"data row0 col10\" >Y</td> \n",
 171 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col11\" class=\"data row0 col11\" >Y</td> \n",
 172 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col12\" class=\"data row0 col12\" >Y</td> \n",
 173 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col13\" class=\"data row0 col13\" >Y</td> \n",
 174 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col14\" class=\"data row0 col14\" >Y</td> \n",
 175 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col15\" class=\"data row0 col15\" >Y</td> \n",
 176 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col16\" class=\"data row0 col16\" >Y</td> \n",
 177 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col17\" class=\"data row0 col17\" >Y</td> \n",
 178 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col18\" class=\"data row0 col18\" >Y</td> \n",
 179 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col19\" class=\"data row0 col19\" >Y</td> \n",
 180 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col20\" class=\"data row0 col20\" >Y</td> \n",
 181 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col21\" class=\"data row0 col21\" >Y</td> \n",
 182 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col22\" class=\"data row0 col22\" >Y</td> \n",
 183 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col23\" class=\"data row0 col23\" >Y</td> \n",
 184 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col24\" class=\"data row0 col24\" >Y</td> \n",
 185 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col25\" class=\"data row0 col25\" >Y</td> \n",
 186 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col26\" class=\"data row0 col26\" >Y</td> \n",
 187 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col27\" class=\"data row0 col27\" >Y</td> \n",
 188 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col28\" class=\"data row0 col28\" >Y</td> \n",
 189 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col29\" class=\"data row0 col29\" >Y</td> \n",
 190 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col30\" class=\"data row0 col30\" >Y</td> \n",
 191 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col31\" class=\"data row0 col31\" >Y</td> \n",
 192 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col32\" class=\"data row0 col32\" ></td> \n",
 193 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col33\" class=\"data row0 col33\" ></td> \n",
 194 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col34\" class=\"data row0 col34\" ></td> \n",
 195 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col35\" class=\"data row0 col35\" ></td> \n",
 196 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col36\" class=\"data row0 col36\" >0</td> \n",
 197 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col37\" class=\"data row0 col37\" >0</td> \n",
 198 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col38\" class=\"data row0 col38\" >0</td> \n",
 199 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col39\" class=\"data row0 col39\" >0</td> \n",
 200 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col40\" class=\"data row0 col40\" ></td> \n",
 201 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col41\" class=\"data row0 col41\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 202 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col42\" class=\"data row0 col42\" >N</td> \n",
 203 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col43\" class=\"data row0 col43\" >N</td> \n",
 204 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col44\" class=\"data row0 col44\" ></td> \n",
 205 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row0_col45\" class=\"data row0 col45\" >0.000000</td> \n",
 206 |        "    </tr>    <tr> \n",
 207 |        "        <th id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229\" class=\"row_heading level0 row1\" >1</th> \n",
 208 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col0\" class=\"data row1 col0\" >127.0.0.1</td> \n",
 209 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col1\" class=\"data row1 col1\" >root</td> \n",
 210 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col2\" class=\"data row1 col2\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 211 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col3\" class=\"data row1 col3\" >Y</td> \n",
 212 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col4\" class=\"data row1 col4\" >Y</td> \n",
 213 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col5\" class=\"data row1 col5\" >Y</td> \n",
 214 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col6\" class=\"data row1 col6\" >Y</td> \n",
 215 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col7\" class=\"data row1 col7\" >Y</td> \n",
 216 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col8\" class=\"data row1 col8\" >Y</td> \n",
 217 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col9\" class=\"data row1 col9\" >Y</td> \n",
 218 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col10\" class=\"data row1 col10\" >Y</td> \n",
 219 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col11\" class=\"data row1 col11\" >Y</td> \n",
 220 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col12\" class=\"data row1 col12\" >Y</td> \n",
 221 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col13\" class=\"data row1 col13\" >Y</td> \n",
 222 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col14\" class=\"data row1 col14\" >Y</td> \n",
 223 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col15\" class=\"data row1 col15\" >Y</td> \n",
 224 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col16\" class=\"data row1 col16\" >Y</td> \n",
 225 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col17\" class=\"data row1 col17\" >Y</td> \n",
 226 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col18\" class=\"data row1 col18\" >Y</td> \n",
 227 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col19\" class=\"data row1 col19\" >Y</td> \n",
 228 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col20\" class=\"data row1 col20\" >Y</td> \n",
 229 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col21\" class=\"data row1 col21\" >Y</td> \n",
 230 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col22\" class=\"data row1 col22\" >Y</td> \n",
 231 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col23\" class=\"data row1 col23\" >Y</td> \n",
 232 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col24\" class=\"data row1 col24\" >Y</td> \n",
 233 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col25\" class=\"data row1 col25\" >Y</td> \n",
 234 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col26\" class=\"data row1 col26\" >Y</td> \n",
 235 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col27\" class=\"data row1 col27\" >Y</td> \n",
 236 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col28\" class=\"data row1 col28\" >Y</td> \n",
 237 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col29\" class=\"data row1 col29\" >Y</td> \n",
 238 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col30\" class=\"data row1 col30\" >Y</td> \n",
 239 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col31\" class=\"data row1 col31\" >Y</td> \n",
 240 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col32\" class=\"data row1 col32\" ></td> \n",
 241 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col33\" class=\"data row1 col33\" ></td> \n",
 242 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col34\" class=\"data row1 col34\" ></td> \n",
 243 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col35\" class=\"data row1 col35\" ></td> \n",
 244 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col36\" class=\"data row1 col36\" >0</td> \n",
 245 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col37\" class=\"data row1 col37\" >0</td> \n",
 246 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col38\" class=\"data row1 col38\" >0</td> \n",
 247 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col39\" class=\"data row1 col39\" >0</td> \n",
 248 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col40\" class=\"data row1 col40\" ></td> \n",
 249 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col41\" class=\"data row1 col41\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 250 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col42\" class=\"data row1 col42\" >N</td> \n",
 251 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col43\" class=\"data row1 col43\" >N</td> \n",
 252 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col44\" class=\"data row1 col44\" ></td> \n",
 253 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row1_col45\" class=\"data row1 col45\" >0.000000</td> \n",
 254 |        "    </tr>    <tr> \n",
 255 |        "        <th id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229\" class=\"row_heading level0 row2\" >2</th> \n",
 256 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col0\" class=\"data row2 col0\" >::1</td> \n",
 257 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col1\" class=\"data row2 col1\" >root</td> \n",
 258 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col2\" class=\"data row2 col2\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 259 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col3\" class=\"data row2 col3\" >Y</td> \n",
 260 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col4\" class=\"data row2 col4\" >Y</td> \n",
 261 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col5\" class=\"data row2 col5\" >Y</td> \n",
 262 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col6\" class=\"data row2 col6\" >Y</td> \n",
 263 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col7\" class=\"data row2 col7\" >Y</td> \n",
 264 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col8\" class=\"data row2 col8\" >Y</td> \n",
 265 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col9\" class=\"data row2 col9\" >Y</td> \n",
 266 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col10\" class=\"data row2 col10\" >Y</td> \n",
 267 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col11\" class=\"data row2 col11\" >Y</td> \n",
 268 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col12\" class=\"data row2 col12\" >Y</td> \n",
 269 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col13\" class=\"data row2 col13\" >Y</td> \n",
 270 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col14\" class=\"data row2 col14\" >Y</td> \n",
 271 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col15\" class=\"data row2 col15\" >Y</td> \n",
 272 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col16\" class=\"data row2 col16\" >Y</td> \n",
 273 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col17\" class=\"data row2 col17\" >Y</td> \n",
 274 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col18\" class=\"data row2 col18\" >Y</td> \n",
 275 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col19\" class=\"data row2 col19\" >Y</td> \n",
 276 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col20\" class=\"data row2 col20\" >Y</td> \n",
 277 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col21\" class=\"data row2 col21\" >Y</td> \n",
 278 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col22\" class=\"data row2 col22\" >Y</td> \n",
 279 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col23\" class=\"data row2 col23\" >Y</td> \n",
 280 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col24\" class=\"data row2 col24\" >Y</td> \n",
 281 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col25\" class=\"data row2 col25\" >Y</td> \n",
 282 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col26\" class=\"data row2 col26\" >Y</td> \n",
 283 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col27\" class=\"data row2 col27\" >Y</td> \n",
 284 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col28\" class=\"data row2 col28\" >Y</td> \n",
 285 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col29\" class=\"data row2 col29\" >Y</td> \n",
 286 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col30\" class=\"data row2 col30\" >Y</td> \n",
 287 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col31\" class=\"data row2 col31\" >Y</td> \n",
 288 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col32\" class=\"data row2 col32\" ></td> \n",
 289 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col33\" class=\"data row2 col33\" ></td> \n",
 290 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col34\" class=\"data row2 col34\" ></td> \n",
 291 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col35\" class=\"data row2 col35\" ></td> \n",
 292 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col36\" class=\"data row2 col36\" >0</td> \n",
 293 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col37\" class=\"data row2 col37\" >0</td> \n",
 294 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col38\" class=\"data row2 col38\" >0</td> \n",
 295 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col39\" class=\"data row2 col39\" >0</td> \n",
 296 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col40\" class=\"data row2 col40\" ></td> \n",
 297 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col41\" class=\"data row2 col41\" ></td> \n",
 298 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col42\" class=\"data row2 col42\" >N</td> \n",
 299 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col43\" class=\"data row2 col43\" >N</td> \n",
 300 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col44\" class=\"data row2 col44\" ></td> \n",
 301 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row2_col45\" class=\"data row2 col45\" >0.000000</td> \n",
 302 |        "    </tr>    <tr> \n",
 303 |        "        <th id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229\" class=\"row_heading level0 row3\" >3</th> \n",
 304 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col0\" class=\"data row3 col0\" >%</td> \n",
 305 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col1\" class=\"data row3 col1\" >root</td> \n",
 306 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col2\" class=\"data row3 col2\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 307 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col3\" class=\"data row3 col3\" >N</td> \n",
 308 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col4\" class=\"data row3 col4\" >N</td> \n",
 309 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col5\" class=\"data row3 col5\" >N</td> \n",
 310 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col6\" class=\"data row3 col6\" >N</td> \n",
 311 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col7\" class=\"data row3 col7\" >N</td> \n",
 312 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col8\" class=\"data row3 col8\" >N</td> \n",
 313 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col9\" class=\"data row3 col9\" >N</td> \n",
 314 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col10\" class=\"data row3 col10\" >N</td> \n",
 315 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col11\" class=\"data row3 col11\" >N</td> \n",
 316 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col12\" class=\"data row3 col12\" >N</td> \n",
 317 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col13\" class=\"data row3 col13\" >N</td> \n",
 318 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col14\" class=\"data row3 col14\" >N</td> \n",
 319 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col15\" class=\"data row3 col15\" >N</td> \n",
 320 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col16\" class=\"data row3 col16\" >N</td> \n",
 321 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col17\" class=\"data row3 col17\" >N</td> \n",
 322 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col18\" class=\"data row3 col18\" >N</td> \n",
 323 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col19\" class=\"data row3 col19\" >N</td> \n",
 324 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col20\" class=\"data row3 col20\" >N</td> \n",
 325 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col21\" class=\"data row3 col21\" >N</td> \n",
 326 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col22\" class=\"data row3 col22\" >N</td> \n",
 327 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col23\" class=\"data row3 col23\" >N</td> \n",
 328 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col24\" class=\"data row3 col24\" >N</td> \n",
 329 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col25\" class=\"data row3 col25\" >N</td> \n",
 330 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col26\" class=\"data row3 col26\" >N</td> \n",
 331 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col27\" class=\"data row3 col27\" >N</td> \n",
 332 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col28\" class=\"data row3 col28\" >N</td> \n",
 333 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col29\" class=\"data row3 col29\" >N</td> \n",
 334 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col30\" class=\"data row3 col30\" >N</td> \n",
 335 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col31\" class=\"data row3 col31\" >N</td> \n",
 336 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col32\" class=\"data row3 col32\" ></td> \n",
 337 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col33\" class=\"data row3 col33\" ></td> \n",
 338 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col34\" class=\"data row3 col34\" ></td> \n",
 339 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col35\" class=\"data row3 col35\" ></td> \n",
 340 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col36\" class=\"data row3 col36\" >0</td> \n",
 341 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col37\" class=\"data row3 col37\" >0</td> \n",
 342 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col38\" class=\"data row3 col38\" >0</td> \n",
 343 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col39\" class=\"data row3 col39\" >0</td> \n",
 344 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col40\" class=\"data row3 col40\" ></td> \n",
 345 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col41\" class=\"data row3 col41\" ></td> \n",
 346 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col42\" class=\"data row3 col42\" >N</td> \n",
 347 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col43\" class=\"data row3 col43\" >N</td> \n",
 348 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col44\" class=\"data row3 col44\" ></td> \n",
 349 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row3_col45\" class=\"data row3 col45\" >0.000000</td> \n",
 350 |        "    </tr>    <tr> \n",
 351 |        "        <th id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229\" class=\"row_heading level0 row4\" >4</th> \n",
 352 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col0\" class=\"data row4 col0\" >localhost</td> \n",
 353 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col1\" class=\"data row4 col1\" >root1</td> \n",
 354 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col2\" class=\"data row4 col2\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 355 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col3\" class=\"data row4 col3\" >Y</td> \n",
 356 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col4\" class=\"data row4 col4\" >Y</td> \n",
 357 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col5\" class=\"data row4 col5\" >Y</td> \n",
 358 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col6\" class=\"data row4 col6\" >Y</td> \n",
 359 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col7\" class=\"data row4 col7\" >Y</td> \n",
 360 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col8\" class=\"data row4 col8\" >Y</td> \n",
 361 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col9\" class=\"data row4 col9\" >Y</td> \n",
 362 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col10\" class=\"data row4 col10\" >Y</td> \n",
 363 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col11\" class=\"data row4 col11\" >Y</td> \n",
 364 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col12\" class=\"data row4 col12\" >Y</td> \n",
 365 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col13\" class=\"data row4 col13\" >N</td> \n",
 366 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col14\" class=\"data row4 col14\" >Y</td> \n",
 367 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col15\" class=\"data row4 col15\" >Y</td> \n",
 368 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col16\" class=\"data row4 col16\" >Y</td> \n",
 369 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col17\" class=\"data row4 col17\" >Y</td> \n",
 370 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col18\" class=\"data row4 col18\" >Y</td> \n",
 371 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col19\" class=\"data row4 col19\" >Y</td> \n",
 372 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col20\" class=\"data row4 col20\" >Y</td> \n",
 373 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col21\" class=\"data row4 col21\" >Y</td> \n",
 374 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col22\" class=\"data row4 col22\" >Y</td> \n",
 375 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col23\" class=\"data row4 col23\" >Y</td> \n",
 376 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col24\" class=\"data row4 col24\" >Y</td> \n",
 377 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col25\" class=\"data row4 col25\" >Y</td> \n",
 378 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col26\" class=\"data row4 col26\" >Y</td> \n",
 379 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col27\" class=\"data row4 col27\" >Y</td> \n",
 380 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col28\" class=\"data row4 col28\" >Y</td> \n",
 381 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col29\" class=\"data row4 col29\" >Y</td> \n",
 382 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col30\" class=\"data row4 col30\" >Y</td> \n",
 383 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col31\" class=\"data row4 col31\" >Y</td> \n",
 384 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col32\" class=\"data row4 col32\" ></td> \n",
 385 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col33\" class=\"data row4 col33\" ></td> \n",
 386 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col34\" class=\"data row4 col34\" ></td> \n",
 387 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col35\" class=\"data row4 col35\" ></td> \n",
 388 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col36\" class=\"data row4 col36\" >0</td> \n",
 389 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col37\" class=\"data row4 col37\" >0</td> \n",
 390 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col38\" class=\"data row4 col38\" >0</td> \n",
 391 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col39\" class=\"data row4 col39\" >0</td> \n",
 392 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col40\" class=\"data row4 col40\" ></td> \n",
 393 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col41\" class=\"data row4 col41\" ></td> \n",
 394 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col42\" class=\"data row4 col42\" >N</td> \n",
 395 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col43\" class=\"data row4 col43\" >N</td> \n",
 396 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col44\" class=\"data row4 col44\" ></td> \n",
 397 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row4_col45\" class=\"data row4 col45\" >0.000000</td> \n",
 398 |        "    </tr>    <tr> \n",
 399 |        "        <th id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229\" class=\"row_heading level0 row5\" >5</th> \n",
 400 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col0\" class=\"data row5 col0\" >hostname</td> \n",
 401 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col1\" class=\"data row5 col1\" >username</td> \n",
 402 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col2\" class=\"data row5 col2\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 403 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col3\" class=\"data row5 col3\" >Y</td> \n",
 404 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col4\" class=\"data row5 col4\" >Y</td> \n",
 405 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col5\" class=\"data row5 col5\" >Y</td> \n",
 406 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col6\" class=\"data row5 col6\" >Y</td> \n",
 407 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col7\" class=\"data row5 col7\" >Y</td> \n",
 408 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col8\" class=\"data row5 col8\" >Y</td> \n",
 409 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col9\" class=\"data row5 col9\" >Y</td> \n",
 410 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col10\" class=\"data row5 col10\" >Y</td> \n",
 411 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col11\" class=\"data row5 col11\" >Y</td> \n",
 412 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col12\" class=\"data row5 col12\" >Y</td> \n",
 413 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col13\" class=\"data row5 col13\" >Y</td> \n",
 414 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col14\" class=\"data row5 col14\" >Y</td> \n",
 415 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col15\" class=\"data row5 col15\" >Y</td> \n",
 416 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col16\" class=\"data row5 col16\" >Y</td> \n",
 417 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col17\" class=\"data row5 col17\" >Y</td> \n",
 418 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col18\" class=\"data row5 col18\" >Y</td> \n",
 419 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col19\" class=\"data row5 col19\" >Y</td> \n",
 420 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col20\" class=\"data row5 col20\" >Y</td> \n",
 421 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col21\" class=\"data row5 col21\" >Y</td> \n",
 422 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col22\" class=\"data row5 col22\" >Y</td> \n",
 423 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col23\" class=\"data row5 col23\" >Y</td> \n",
 424 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col24\" class=\"data row5 col24\" >Y</td> \n",
 425 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col25\" class=\"data row5 col25\" >Y</td> \n",
 426 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col26\" class=\"data row5 col26\" >Y</td> \n",
 427 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col27\" class=\"data row5 col27\" >Y</td> \n",
 428 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col28\" class=\"data row5 col28\" >Y</td> \n",
 429 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col29\" class=\"data row5 col29\" >Y</td> \n",
 430 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col30\" class=\"data row5 col30\" >Y</td> \n",
 431 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col31\" class=\"data row5 col31\" >Y</td> \n",
 432 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col32\" class=\"data row5 col32\" ></td> \n",
 433 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col33\" class=\"data row5 col33\" ></td> \n",
 434 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col34\" class=\"data row5 col34\" ></td> \n",
 435 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col35\" class=\"data row5 col35\" ></td> \n",
 436 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col36\" class=\"data row5 col36\" >0</td> \n",
 437 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col37\" class=\"data row5 col37\" >0</td> \n",
 438 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col38\" class=\"data row5 col38\" >0</td> \n",
 439 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col39\" class=\"data row5 col39\" >0</td> \n",
 440 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col40\" class=\"data row5 col40\" ></td> \n",
 441 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col41\" class=\"data row5 col41\" ></td> \n",
 442 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col42\" class=\"data row5 col42\" >N</td> \n",
 443 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col43\" class=\"data row5 col43\" >N</td> \n",
 444 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col44\" class=\"data row5 col44\" ></td> \n",
 445 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row5_col45\" class=\"data row5 col45\" >0.000000</td> \n",
 446 |        "    </tr>    <tr> \n",
 447 |        "        <th id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229\" class=\"row_heading level0 row6\" >6</th> \n",
 448 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col0\" class=\"data row6 col0\" >192.168.%</td> \n",
 449 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col1\" class=\"data row6 col1\" >root</td> \n",
 450 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col2\" class=\"data row6 col2\" >*81F5E21E35407D884A6CD4A731AEBFB6AF209E1B</td> \n",
 451 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col3\" class=\"data row6 col3\" >Y</td> \n",
 452 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col4\" class=\"data row6 col4\" >Y</td> \n",
 453 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col5\" class=\"data row6 col5\" >Y</td> \n",
 454 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col6\" class=\"data row6 col6\" >Y</td> \n",
 455 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col7\" class=\"data row6 col7\" >Y</td> \n",
 456 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col8\" class=\"data row6 col8\" >Y</td> \n",
 457 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col9\" class=\"data row6 col9\" >Y</td> \n",
 458 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col10\" class=\"data row6 col10\" >Y</td> \n",
 459 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col11\" class=\"data row6 col11\" >Y</td> \n",
 460 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col12\" class=\"data row6 col12\" >Y</td> \n",
 461 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col13\" class=\"data row6 col13\" >N</td> \n",
 462 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col14\" class=\"data row6 col14\" >Y</td> \n",
 463 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col15\" class=\"data row6 col15\" >Y</td> \n",
 464 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col16\" class=\"data row6 col16\" >Y</td> \n",
 465 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col17\" class=\"data row6 col17\" >Y</td> \n",
 466 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col18\" class=\"data row6 col18\" >Y</td> \n",
 467 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col19\" class=\"data row6 col19\" >Y</td> \n",
 468 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col20\" class=\"data row6 col20\" >Y</td> \n",
 469 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col21\" class=\"data row6 col21\" >Y</td> \n",
 470 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col22\" class=\"data row6 col22\" >Y</td> \n",
 471 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col23\" class=\"data row6 col23\" >Y</td> \n",
 472 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col24\" class=\"data row6 col24\" >Y</td> \n",
 473 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col25\" class=\"data row6 col25\" >Y</td> \n",
 474 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col26\" class=\"data row6 col26\" >Y</td> \n",
 475 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col27\" class=\"data row6 col27\" >Y</td> \n",
 476 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col28\" class=\"data row6 col28\" >Y</td> \n",
 477 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col29\" class=\"data row6 col29\" >Y</td> \n",
 478 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col30\" class=\"data row6 col30\" >Y</td> \n",
 479 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col31\" class=\"data row6 col31\" >Y</td> \n",
 480 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col32\" class=\"data row6 col32\" ></td> \n",
 481 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col33\" class=\"data row6 col33\" ></td> \n",
 482 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col34\" class=\"data row6 col34\" ></td> \n",
 483 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col35\" class=\"data row6 col35\" ></td> \n",
 484 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col36\" class=\"data row6 col36\" >0</td> \n",
 485 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col37\" class=\"data row6 col37\" >0</td> \n",
 486 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col38\" class=\"data row6 col38\" >0</td> \n",
 487 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col39\" class=\"data row6 col39\" >0</td> \n",
 488 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col40\" class=\"data row6 col40\" ></td> \n",
 489 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col41\" class=\"data row6 col41\" ></td> \n",
 490 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col42\" class=\"data row6 col42\" >N</td> \n",
 491 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col43\" class=\"data row6 col43\" >N</td> \n",
 492 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col44\" class=\"data row6 col44\" ></td> \n",
 493 |        "        <td id=\"T_4a8bdd7e_0ade_11e8_9727_000c29730229row6_col45\" class=\"data row6 col45\" >0.000000</td> \n",
 494 |        "    </tr></tbody> \n",
 495 |        "</table> "
 496 |       ],
 497 |       "text/plain": [
 498 |        "<pandas.io.formats.style.Styler at 0x7f6453212c90>"
 499 |       ]
 500 |      },
 501 |      "execution_count": 20,
 502 |      "metadata": {},
 503 |      "output_type": "execute_result"
 504 |     }
 505 |    ],
 506 |    "source": [
 507 |     "import pandas as pd\n",
 508 |     "\n",
 509 |     "rw_df=pd.DataFrame([t for t in rows])\n",
 510 |     "display_prettify(rw_df)"
 511 |    ]
 512 |   },
 513 |   {
 514 |    "cell_type": "markdown",
 515 |    "metadata": {},
 516 |    "source": [
 517 |     "### 创建一个表并且插入数据"
 518 |    ]
 519 |   },
 520 |   {
 521 |    "cell_type": "code",
 522 |    "execution_count": 27,
 523 |    "metadata": {},
 524 |    "outputs": [],
 525 |    "source": [
 526 |     "import MySQLdb as mdb\n",
 527 |     "\n",
 528 |     "# conn 创建全局连接\n",
 529 |     "conn = mdb.connect(ip,user,pwd,dnname,port);\n",
 530 |     "with conn:\n",
 531 |     "    curs = conn.cursor() # 获取 cursor\n",
 532 |     "    # 创建数据表 writers(id,name)\n",
 533 |     "    curs.execute(\"CREATE TABLE IF NOT EXISTS \\\n",
 534 |     "        Writers(Id INT PRIMARY KEY AUTO_INCREMENT, Name VARCHAR(25))\")\n",
 535 |     "    # 插入 5 条数据\n",
 536 |     "    curs.execute(\"INSERT INTO Writers(Name) VALUES('Jack London')\")\n",
 537 |     "    curs.execute(\"INSERT INTO Writers(Name) VALUES('Honore de Balzac')\")\n",
 538 |     "    curs.execute(\"INSERT INTO Writers(Name) VALUES('Lion Feuchtwanger')\")\n",
 539 |     "    curs.execute(\"INSERT INTO Writers(Name) VALUES('Emile Zola')\")\n",
 540 |     "    curs.execute(\"INSERT INTO Writers(Name) VALUES('Truman Capote')\")\n",
 541 |     "    \n",
 542 |     "    # conn.commit()\n",
 543 |     "    \n",
 544 |     "curs.execute('SELECT * FROM Writers;')\n",
 545 |     "rows=curs.fetchall()\n",
 546 |     "conn.close()\n",
 547 |     "curs.close()"
 548 |    ]
 549 |   },
 550 |   {
 551 |    "cell_type": "code",
 552 |    "execution_count": 28,
 553 |    "metadata": {},
 554 |    "outputs": [
 555 |     {
 556 |      "data": {
 557 |       "text/html": [
 558 |        "<style  type=\"text/css\" >\n",
 559 |        "    #T_717c680c_0ae0_11e8_9727_000c29730229 tr:hover {\n",
 560 |        "          background-color: #ffff99;\n",
 561 |        "    }    #T_717c680c_0ae0_11e8_9727_000c29730229 th {\n",
 562 |        "          font-size: 100%;\n",
 563 |        "          text-align: center;\n",
 564 |        "    }    #T_717c680c_0ae0_11e8_9727_000c29730229 td {\n",
 565 |        "          text-align: left;\n",
 566 |        "    }    #T_717c680c_0ae0_11e8_9727_000c29730229 caption {\n",
 567 |        "          caption-side: left;\n",
 568 |        "    }</style>  \n",
 569 |        "<table id=\"T_717c680c_0ae0_11e8_9727_000c29730229\" ><caption>Hover to highlight.</caption> \n",
 570 |        "<thead>    <tr> \n",
 571 |        "        <th class=\"blank level0\" ></th> \n",
 572 |        "        <th class=\"col_heading level0 col0\" >0</th> \n",
 573 |        "        <th class=\"col_heading level0 col1\" >1</th> \n",
 574 |        "    </tr></thead> \n",
 575 |        "<tbody>    <tr> \n",
 576 |        "        <th id=\"T_717c680c_0ae0_11e8_9727_000c29730229\" class=\"row_heading level0 row0\" >0</th> \n",
 577 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row0_col0\" class=\"data row0 col0\" >1</td> \n",
 578 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row0_col1\" class=\"data row0 col1\" >Jack London</td> \n",
 579 |        "    </tr>    <tr> \n",
 580 |        "        <th id=\"T_717c680c_0ae0_11e8_9727_000c29730229\" class=\"row_heading level0 row1\" >1</th> \n",
 581 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row1_col0\" class=\"data row1 col0\" >2</td> \n",
 582 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row1_col1\" class=\"data row1 col1\" >Honore de Balzac</td> \n",
 583 |        "    </tr>    <tr> \n",
 584 |        "        <th id=\"T_717c680c_0ae0_11e8_9727_000c29730229\" class=\"row_heading level0 row2\" >2</th> \n",
 585 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row2_col0\" class=\"data row2 col0\" >3</td> \n",
 586 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row2_col1\" class=\"data row2 col1\" >Lion Feuchtwanger</td> \n",
 587 |        "    </tr>    <tr> \n",
 588 |        "        <th id=\"T_717c680c_0ae0_11e8_9727_000c29730229\" class=\"row_heading level0 row3\" >3</th> \n",
 589 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row3_col0\" class=\"data row3 col0\" >4</td> \n",
 590 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row3_col1\" class=\"data row3 col1\" >Emile Zola</td> \n",
 591 |        "    </tr>    <tr> \n",
 592 |        "        <th id=\"T_717c680c_0ae0_11e8_9727_000c29730229\" class=\"row_heading level0 row4\" >4</th> \n",
 593 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row4_col0\" class=\"data row4 col0\" >5</td> \n",
 594 |        "        <td id=\"T_717c680c_0ae0_11e8_9727_000c29730229row4_col1\" class=\"data row4 col1\" >Truman Capote</td> \n",
 595 |        "    </tr></tbody> \n",
 596 |        "</table> "
 597 |       ],
 598 |       "text/plain": [
 599 |        "<pandas.io.formats.style.Styler at 0x7f6452f61fd0>"
 600 |       ]
 601 |      },
 602 |      "execution_count": 28,
 603 |      "metadata": {},
 604 |      "output_type": "execute_result"
 605 |     }
 606 |    ],
 607 |    "source": [
 608 |     "display_prettify(pd.DataFrame([rw for rw in rows]))"
 609 |    ]
 610 |   },
 611 |   {
 612 |    "cell_type": "markdown",
 613 |    "metadata": {},
 614 |    "source": [
 615 |     "### python 获取表数据并取行数据中单个数据"
 616 |    ]
 617 |   },
 618 |   {
 619 |    "cell_type": "code",
 620 |    "execution_count": 53,
 621 |    "metadata": {},
 622 |    "outputs": [
 623 |     {
 624 |      "name": "stdout",
 625 |      "output_type": "stream",
 626 |      "text": [
 627 |       "1 Jack London\n",
 628 |       "2 Honore de Balzac\n",
 629 |       "3 Guy de Maupasant\n",
 630 |       "4 Guy de Maupasant\n",
 631 |       "5 Truman Capote\n",
 632 |       "-----使用字典游标获取结果集，并通过字段名访问值-----\n",
 633 |       "1 Jack London\n",
 634 |       "2 Honore de Balzac\n",
 635 |       "3 Guy de Maupasant\n",
 636 |       "4 Guy de Maupasant\n",
 637 |       "5 Truman Capote\n"
 638 |      ]
 639 |     }
 640 |    ],
 641 |    "source": [
 642 |     "import MySQLdb as mdb\n",
 643 |     "\n",
 644 |     "# conn 创建全局连接\n",
 645 |     "conn = mdb.connect(ip,user,pwd,dnname,port);\n",
 646 |     "\n",
 647 |     "with conn:\n",
 648 |     "    curs = conn.cursor() # 获取 cursor\n",
 649 |     "    curs.execute(\"SELECT * FROM Writers\")\n",
 650 |     "    \n",
 651 |     "    numrows = int(curs.rowcount) # 获取行数\n",
 652 |     "    for i in range(numrows): # 循环取行数据\n",
 653 |     "        row = curs.fetchone() # 每次取出一行数据，同时指针下移\n",
 654 |     "        print row[0], row[1]\n",
 655 |     "        \n",
 656 |     "    print ('-----使用字典游标获取结果集，并通过字段名访问值-----')\n",
 657 |     "    curs = conn.cursor(mdb.cursors.DictCursor)\n",
 658 |     "    curs.execute(\"SELECT * FROM Writers\")\n",
 659 |     "    rows3=curs.fetchall()\n",
 660 |     "    for row in rows3:\n",
 661 |     "        print \"%s %s\" % (row[\"Id\"], row[\"Name\"])\n",
 662 |     "\n",
 663 |     "conn.close()\n",
 664 |     "curs.close()"
 665 |    ]
 666 |   },
 667 |   {
 668 |    "cell_type": "markdown",
 669 |    "metadata": {},
 670 |    "source": [
 671 |     "### Prepared Statements 查询（更安全方便）"
 672 |    ]
 673 |   },
 674 |   {
 675 |    "cell_type": "code",
 676 |    "execution_count": 56,
 677 |    "metadata": {},
 678 |    "outputs": [
 679 |     {
 680 |      "name": "stdout",
 681 |      "output_type": "stream",
 682 |      "text": [
 683 |       "Number of rows updated: 1\n"
 684 |      ]
 685 |     }
 686 |    ],
 687 |    "source": [
 688 |     "import MySQLdb as mdb\n",
 689 |     "\n",
 690 |     "conn = mdb.connect(ip,user,pwd,dnname,port);\n",
 691 |     "with conn:\n",
 692 |     "    curs = conn.cursor()\n",
 693 |     "    # 通过组装sql 进行查询操作\n",
 694 |     "    curs.execute(\"UPDATE Writers SET Name = %s WHERE Id = %s\",(\"Lion Feuchtwanger\", \"3\"))\n",
 695 |     "    # 获取影响多少行\n",
 696 |     "    print \"Number of rows updated: %d\" % curs.rowcount\n",
 697 |     "\n",
 698 |     "conn.commit() \n",
 699 |     "conn.close()\n",
 700 |     "curs.close()"
 701 |    ]
 702 |   },
 703 |   {
 704 |    "cell_type": "markdown",
 705 |    "metadata": {},
 706 |    "source": [
 707 |     "### 把图片用二进制存入 MySQL\n",
 708 |     "- BLOB (Binary Large Object)，即较大的二进制对象字段\n",
 709 |     "- escape_string \n",
 710 |     "    - 字符转义函数\n",
 711 |     "- CREATE TABLE Images(Id INT PRIMARY KEY AUTO_INCREMENT, Data MEDIUMBLOB);"
 712 |    ]
 713 |   },
 714 |   {
 715 |    "cell_type": "code",
 716 |    "execution_count": 64,
 717 |    "metadata": {},
 718 |    "outputs": [
 719 |     {
 720 |      "name": "stderr",
 721 |      "output_type": "stream",
 722 |      "text": [
 723 |       "/root/anaconda2/lib/python2.7/site-packages/ipykernel/__main__.py:9: Warning: Table 'Images' already exists\n"
 724 |      ]
 725 |     }
 726 |    ],
 727 |    "source": [
 728 |     "import MySQLdb as mdb\n",
 729 |     "import sys\n",
 730 |     "\n",
 731 |     "# conn 创建全局连接\n",
 732 |     "conn = mdb.connect(ip,user,pwd,dnname,port);\n",
 733 |     "with conn:\n",
 734 |     "    curs = conn.cursor() # 获取 cursor\n",
 735 |     "    # 创建数据表 writers(id,name)\n",
 736 |     "    curs.execute(\"CREATE TABLE if not exists \\\n",
 737 |     "        Images(Id INT PRIMARY KEY AUTO_INCREMENT, Data MEDIUMBLOB);\")\n",
 738 |     "curs.close()\n",
 739 |     "\n",
 740 |     "try:\n",
 741 |     "    fin = open(\"/home/synway/kngines1.jpg\")\n",
 742 |     "    img = fin.read() # 读入文件流\n",
 743 |     "    fin.close()\n",
 744 |     "except IOError, e:\n",
 745 |     "    print \"Error %d: %s\" % (e.args[0],e.args[1])\n",
 746 |     "    sys.exit(1)\n",
 747 |     "try:\n",
 748 |     "    cursor = conn.cursor()\n",
 749 |     "    cursor.execute(\"INSERT INTO Images SET Data='%s'\" % mdb.escape_string(img))\n",
 750 |     "    conn.commit()  # 提交数据\n",
 751 |     "    cursor.close()\n",
 752 |     "    conn.close()\n",
 753 |     "except mdb.Error, e:\n",
 754 |     "    print \"Error %d: %s\" % (e.args[0],e.args[1])\n",
 755 |     "    sys.exit(1)"
 756 |    ]
 757 |   },
 758 |   {
 759 |    "cell_type": "markdown",
 760 |    "metadata": {},
 761 |    "source": [
 762 |     "### 从数据库中把图片读出来"
 763 |    ]
 764 |   },
 765 |   {
 766 |    "cell_type": "code",
 767 |    "execution_count": 65,
 768 |    "metadata": {
 769 |     "collapsed": true
 770 |    },
 771 |    "outputs": [],
 772 |    "source": [
 773 |     "import MySQLdb as mdb\n",
 774 |     "import sys\n",
 775 |     "try:\n",
 776 |     "    conn = mdb.connect(ip,user,pwd,dnname,port);\n",
 777 |     "    cursor = conn.cursor() \n",
 778 |     "    cursor.execute(\"SELECT Data FROM Images LIMIT 1\") # 执行查询\n",
 779 |     "    \n",
 780 |     "    fout = open('image.png','wb')  # 使用二进制进行写文件\n",
 781 |     "    fout.write(cursor.fetchone()[0])\n",
 782 |     "    \n",
 783 |     "    fout.close() # 关闭输出流\n",
 784 |     "    cursor.close() # 关闭游标\n",
 785 |     "    conn.close() # 关闭连接\n",
 786 |     "except IOError, e:\n",
 787 |     "    print \"Error %d: %s\" % (e.args[0],e.args[1])\n",
 788 |     "    sys.exit(1)"
 789 |    ]
 790 |   },
 791 |   {
 792 |    "cell_type": "markdown",
 793 |    "metadata": {},
 794 |    "source": [
 795 |     "### Transaction，即事务（手动提交，自动回滚）"
 796 |    ]
 797 |   },
 798 |   {
 799 |    "cell_type": "markdown",
 800 |    "metadata": {},
 801 |    "source": [
 802 |     "#### 查询默认引擎信息\n",
 803 |     "- MyISAM\n",
 804 |     "    - 不支持事务；\n",
 805 |     "    - 内部的复杂机制很少，特别适应于读多写少的应用；\n",
 806 |     "- InnoDB\n",
 807 |     "    - 事务型存储引擎，适合处理大量的短期事务；"
 808 |    ]
 809 |   },
 810 |   {
 811 |    "cell_type": "code",
 812 |    "execution_count": 74,
 813 |    "metadata": {},
 814 |    "outputs": [
 815 |     {
 816 |      "data": {
 817 |       "text/html": [
 818 |        "<style  type=\"text/css\" >\n",
 819 |        "    #T_a7386212_0ae9_11e8_9727_000c29730229 tr:hover {\n",
 820 |        "          background-color: #ffff99;\n",
 821 |        "    }    #T_a7386212_0ae9_11e8_9727_000c29730229 th {\n",
 822 |        "          font-size: 100%;\n",
 823 |        "          text-align: center;\n",
 824 |        "    }    #T_a7386212_0ae9_11e8_9727_000c29730229 td {\n",
 825 |        "          text-align: left;\n",
 826 |        "    }    #T_a7386212_0ae9_11e8_9727_000c29730229 caption {\n",
 827 |        "          caption-side: left;\n",
 828 |        "    }</style>  \n",
 829 |        "<table id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" ><caption>Hover to highlight.</caption> \n",
 830 |        "<thead>    <tr> \n",
 831 |        "        <th class=\"blank level0\" ></th> \n",
 832 |        "        <th class=\"col_heading level0 col0\" >Engine_name</th> \n",
 833 |        "        <th class=\"col_heading level0 col1\" >Support</th> \n",
 834 |        "        <th class=\"col_heading level0 col2\" >Comment</th> \n",
 835 |        "        <th class=\"col_heading level0 col3\" >Transactions</th> \n",
 836 |        "        <th class=\"col_heading level0 col4\" >XA</th> \n",
 837 |        "        <th class=\"col_heading level0 col5\" >Savepoints</th> \n",
 838 |        "    </tr></thead> \n",
 839 |        "<tbody>    <tr> \n",
 840 |        "        <th id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" class=\"row_heading level0 row0\" >0</th> \n",
 841 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row0_col0\" class=\"data row0 col0\" >MRG_MyISAM</td> \n",
 842 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row0_col1\" class=\"data row0 col1\" >YES</td> \n",
 843 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row0_col2\" class=\"data row0 col2\" >Collection of identical MyISAM tables</td> \n",
 844 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row0_col3\" class=\"data row0 col3\" >NO</td> \n",
 845 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row0_col4\" class=\"data row0 col4\" >NO</td> \n",
 846 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row0_col5\" class=\"data row0 col5\" >NO</td> \n",
 847 |        "    </tr>    <tr> \n",
 848 |        "        <th id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" class=\"row_heading level0 row1\" >1</th> \n",
 849 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row1_col0\" class=\"data row1 col0\" >CSV</td> \n",
 850 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row1_col1\" class=\"data row1 col1\" >YES</td> \n",
 851 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row1_col2\" class=\"data row1 col2\" >CSV storage engine</td> \n",
 852 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row1_col3\" class=\"data row1 col3\" >NO</td> \n",
 853 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row1_col4\" class=\"data row1 col4\" >NO</td> \n",
 854 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row1_col5\" class=\"data row1 col5\" >NO</td> \n",
 855 |        "    </tr>    <tr> \n",
 856 |        "        <th id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" class=\"row_heading level0 row2\" >2</th> \n",
 857 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row2_col0\" class=\"data row2 col0\" >Aria</td> \n",
 858 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row2_col1\" class=\"data row2 col1\" >YES</td> \n",
 859 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row2_col2\" class=\"data row2 col2\" >Crash-safe tables with MyISAM heritage</td> \n",
 860 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row2_col3\" class=\"data row2 col3\" >NO</td> \n",
 861 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row2_col4\" class=\"data row2 col4\" >NO</td> \n",
 862 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row2_col5\" class=\"data row2 col5\" >NO</td> \n",
 863 |        "    </tr>    <tr> \n",
 864 |        "        <th id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" class=\"row_heading level0 row3\" >3</th> \n",
 865 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row3_col0\" class=\"data row3 col0\" >MyISAM</td> \n",
 866 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row3_col1\" class=\"data row3 col1\" >YES</td> \n",
 867 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row3_col2\" class=\"data row3 col2\" >MyISAM storage engine</td> \n",
 868 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row3_col3\" class=\"data row3 col3\" >NO</td> \n",
 869 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row3_col4\" class=\"data row3 col4\" >NO</td> \n",
 870 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row3_col5\" class=\"data row3 col5\" >NO</td> \n",
 871 |        "    </tr>    <tr> \n",
 872 |        "        <th id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" class=\"row_heading level0 row4\" >4</th> \n",
 873 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row4_col0\" class=\"data row4 col0\" >MEMORY</td> \n",
 874 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row4_col1\" class=\"data row4 col1\" >YES</td> \n",
 875 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row4_col2\" class=\"data row4 col2\" >Hash based, stored in memory, useful for temporary tables</td> \n",
 876 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row4_col3\" class=\"data row4 col3\" >NO</td> \n",
 877 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row4_col4\" class=\"data row4 col4\" >NO</td> \n",
 878 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row4_col5\" class=\"data row4 col5\" >NO</td> \n",
 879 |        "    </tr>    <tr> \n",
 880 |        "        <th id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" class=\"row_heading level0 row5\" >5</th> \n",
 881 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row5_col0\" class=\"data row5 col0\" >InnoDB</td> \n",
 882 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row5_col1\" class=\"data row5 col1\" >DEFAULT</td> \n",
 883 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row5_col2\" class=\"data row5 col2\" >Supports transactions, row-level locking, foreign keys and encryption for tables</td> \n",
 884 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row5_col3\" class=\"data row5 col3\" >YES</td> \n",
 885 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row5_col4\" class=\"data row5 col4\" >YES</td> \n",
 886 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row5_col5\" class=\"data row5 col5\" >YES</td> \n",
 887 |        "    </tr>    <tr> \n",
 888 |        "        <th id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" class=\"row_heading level0 row6\" >6</th> \n",
 889 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row6_col0\" class=\"data row6 col0\" >SEQUENCE</td> \n",
 890 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row6_col1\" class=\"data row6 col1\" >YES</td> \n",
 891 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row6_col2\" class=\"data row6 col2\" >Generated tables filled with sequential values</td> \n",
 892 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row6_col3\" class=\"data row6 col3\" >YES</td> \n",
 893 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row6_col4\" class=\"data row6 col4\" >NO</td> \n",
 894 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row6_col5\" class=\"data row6 col5\" >YES</td> \n",
 895 |        "    </tr>    <tr> \n",
 896 |        "        <th id=\"T_a7386212_0ae9_11e8_9727_000c29730229\" class=\"row_heading level0 row7\" >7</th> \n",
 897 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row7_col0\" class=\"data row7 col0\" >PERFORMANCE_SCHEMA</td> \n",
 898 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row7_col1\" class=\"data row7 col1\" >YES</td> \n",
 899 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row7_col2\" class=\"data row7 col2\" >Performance Schema</td> \n",
 900 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row7_col3\" class=\"data row7 col3\" >NO</td> \n",
 901 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row7_col4\" class=\"data row7 col4\" >NO</td> \n",
 902 |        "        <td id=\"T_a7386212_0ae9_11e8_9727_000c29730229row7_col5\" class=\"data row7 col5\" >NO</td> \n",
 903 |        "    </tr></tbody> \n",
 904 |        "</table> "
 905 |       ],
 906 |       "text/plain": [
 907 |        "<pandas.io.formats.style.Styler at 0x7f6452f80510>"
 908 |       ]
 909 |      },
 910 |      "execution_count": 74,
 911 |      "metadata": {},
 912 |      "output_type": "execute_result"
 913 |     }
 914 |    ],
 915 |    "source": [
 916 |     "import MySQLdb as mdb\n",
 917 |     "import sys\n",
 918 |     "\n",
 919 |     "conn = mdb.connect(ip,user,pwd,dnname,port);\n",
 920 |     "cursor = conn.cursor()\n",
 921 |     "cursor.execute('show engines;')\n",
 922 |     "rows=cursor.fetchall()\n",
 923 |     "\n",
 924 |     "conn.close()\n",
 925 |     "cursor.close()\n",
 926 |     "\n",
 927 |     "engines_df=pd.DataFrame([rw for rw in rows], columns=['Engine_name','Support','Comment','Transactions','XA','Savepoints'])\n",
 928 |     "display_prettify(engines_df)"
 929 |    ]
 930 |   },
 931 |   {
 932 |    "cell_type": "code",
 933 |    "execution_count": 79,
 934 |    "metadata": {},
 935 |    "outputs": [],
 936 |    "source": [
 937 |     "import MySQLdb as mdb\n",
 938 |     "import sys\n",
 939 |     "try:\n",
 940 |     "    conn = mdb.connect(ip,user,pwd,dnname,port);\n",
 941 |     "    cursor = conn.cursor()\n",
 942 |     "    \n",
 943 |     "    # 如果某个数据库支持事务，会自动开启\n",
 944 |     "    # MariDB，自动开启事务（若是 MyISAM 引擎则不会）\n",
 945 |     "    cursor.execute(\"UPDATE Writers SET Name = %s WHERE Id = %s\",(\"Leo Tolstoy\", \"1\"))\n",
 946 |     "    cursor.execute(\"UPDATE Writers SET Name = %s WHERE Id = %s\",(\"Boris Pasternak\", \"2\"))\n",
 947 |     "    cursor.execute(\"UPDATE Writer SET Name = %s WHERE Id = %s\",(\"Leonid Leonov\", \"3\"))\n",
 948 |     "    \n",
 949 |     "    # 事务的特性 1、原子性的手动提交\n",
 950 |     "    conn.commit()\n",
 951 |     "    cursor.close()\n",
 952 |     "    conn.close()\n",
 953 |     "except mdb.Error, e:\n",
 954 |     "    # 若出现错误，则回滚，即上面三条语句要么执行，要么不执行\n",
 955 |     "    conn.rollback()\n",
 956 |     "    print \"Error %d: %s\" % (e.args[0],e.args[1])"
 957 |    ]
 958 |   },
 959 |   {
 960 |    "cell_type": "markdown",
 961 |    "metadata": {},
 962 |    "source": [
 963 |     "<font color='gray'>注:<br />\n",
 964 |     "（1）因为不存在 writer 表（SQL 第三条语句），所以出现错误：Error 1146: Table ‘test.writer’ doesn’t exist <br />\n",
 965 |     "（2）出现错误，触发异常处理， 3 条语句的前两条会自动变成没有执行，结果不变.<br />\n",
 966 |     "（3）如果本代码放到一个 MyISAM 引擎表，前两句会执行，第三句不会；如果是 INNDB 引\n",
 967 |     "擎，则都不会执行。（事务特性）</font>"
 968 |    ]
 969 |   }
 970 |  ],
 971 |  "metadata": {
 972 |   "kernelspec": {
 973 |    "display_name": "Python 2",
 974 |    "language": "python",
 975 |    "name": "python2"
 976 |   },
 977 |   "language_info": {
 978 |    "codemirror_mode": {
 979 |     "name": "ipython",
 980 |     "version": 2
 981 |    },
 982 |    "file_extension": ".py",
 983 |    "mimetype": "text/x-python",
 984 |    "name": "python",
 985 |    "nbconvert_exporter": "python",
 986 |    "pygments_lexer": "ipython2",
 987 |    "version": "2.7.13"
 988 |   },
 989 |   "toc": {
 990 |    "nav_menu": {},
 991 |    "number_sections": true,
 992 |    "sideBar": true,
 993 |    "skip_h1_title": false,
 994 |    "toc_cell": false,
 995 |    "toc_position": {
 996 |     "height": "454px",
 997 |     "left": "0px",
 998 |     "right": "831.2px",
 999 |     "top": "107px",
1000 |     "width": "212px"
1001 |    },
1002 |    "toc_section_display": "block",
1003 |    "toc_window_display": true
1004 |   }
1005 |  },
1006 |  "nbformat": 4,
1007 |  "nbformat_minor": 2
1008 | }
1009 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Climb_Python
 2 | 目前任职大数据开发工作，日常开发使用Python作为数据分析工具，在此比较常用的方面知识或难点总结、整理出来，以此分享，谢谢！
 3 | * Anaconda docs
 4 |   * Anaconda环境安装以及搭建Python多内核环境.doc
 5 |   * 简单分析脚本
 6 |     * Anaconda2_infos_analysis.ipynb
 7 |     * Anaconda3_infos_analysis.ipynb
 8 | 
 9 | * 绘制某段时间内用户增加趋势图
10 |   * users_rise_up_period.ipynb
11 |   * users_rise_up_period_data
12 |  
13 | * 爬取糗事百科段子信息
14 |   * [博文: http://blog.csdn.net/qq_24452475/article/details/79122259](http://blog.csdn.net/qq_24452475/article/details/79122259)
15 |   * spider_qiushibaike_content_datas.ipynb
16 |   * spider_qiushibaike_content_datas.py
17 | 
18 | * 爬取公务员招考信息（2018）
19 |   * [博文: http://blog.csdn.net/qq_24452475/article/details/79156758](http://blog.csdn.net/qq_24452475/article/details/79156758)
20 |   * spider_huatu_civil_servant_post_metas.ipynb
21 |   * post_metas.csv
22 | 
23 | * 地址转换：根据地名爬取经纬度并计算geohash值
24 |   * [博文: http://blog.csdn.net/qq_24452475/article/details/79183861](http://blog.csdn.net/qq_24452475/article/details/79183861)
25 |   * lng_lat_2_geohash_two_way.ipynb
26 | 
27 | * 爬取 PyODPS[latest] 并转换为 PDF
28 |   * [博文: http://blog.csdn.net/qq_24452475/article/details/79248953](http://blog.csdn.net/qq_24452475/article/details/79248953)
29 |   * Python_PyODPS_HTML_to_PDF.ipynb
30 | 
31 | * Python操作 MariaDB 实例教程手册
32 |   * 包含Python操作 MariaDB、执行SQL语句、获取、遍历结果集、图片入库、事务等代码示例
33 |   * Python操作 MariaDB 实例教程手册_代码.ipynb
34 | 
35 | * Jupyter 常用 魔术命令（magics）总结
36 |   * Built-in magic commands
37 |   * Python_Common_Magic_Samples.ipynb
38 | 


--------------------------------------------------------------------------------
/lng_lat_2_geohash_two_way.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "## 主要实现\n",
  8 |     "- 批量查询位置点 经纬度等信息\n",
  9 |     "- 经纬度转换为 geohash块、\n",
 10 |     "- 目标geohash 临近geohash块\n",
 11 |     "    - 九宫格"
 12 |    ]
 13 |   },
 14 |   {
 15 |    "cell_type": "markdown",
 16 |    "metadata": {},
 17 |    "source": [
 18 |     "### Note\n",
 19 |     "- 查询位置列表， 需<font color=#FF1953>提前提供</font>"
 20 |    ]
 21 |   },
 22 |   {
 23 |    "cell_type": "code",
 24 |    "execution_count": 5,
 25 |    "metadata": {
 26 |     "collapsed": true
 27 |    },
 28 |    "outputs": [],
 29 |    "source": [
 30 |     "city_lis=['北京', '上海', '郑州']"
 31 |    ]
 32 |   },
 33 |   {
 34 |    "cell_type": "markdown",
 35 |    "metadata": {},
 36 |    "source": [
 37 |     "### 获取位置地点经纬度等信息\n",
 38 |     "- 获取经纬度等信息\n",
 39 |     "- 计算 geohash"
 40 |    ]
 41 |   },
 42 |   {
 43 |    "cell_type": "code",
 44 |    "execution_count": 6,
 45 |    "metadata": {
 46 |     "collapsed": true
 47 |    },
 48 |    "outputs": [],
 49 |    "source": [
 50 |     "import pandas as pd\n",
 51 |     "import mzgeohash\n",
 52 |     "import urllib2\n",
 53 |     "import urllib\n",
 54 |     "import json"
 55 |    ]
 56 |   },
 57 |   {
 58 |    "cell_type": "code",
 59 |    "execution_count": 23,
 60 |    "metadata": {},
 61 |    "outputs": [],
 62 |    "source": [
 63 |     "'''\n",
 64 |     "根据位置名称，获取经纬度等信息\n",
 65 |     "'''\n",
 66 |     "def get_metas_from_baidu(city):\n",
 67 |     "    metas={}\n",
 68 |     "    metas['key']='f247cdb592eb43ebac6ccd27f796e2d2'\n",
 69 |     "    metas['address']=city   # 城市名称\n",
 70 |     "    \n",
 71 |     "    data=urllib.urlencode(metas)\n",
 72 |     "    url='http://api.map.baidu.com/geocoder?output=json&'+urllib.urlencode(metas)\n",
 73 |     "    # 注释 url='http://api.map.baidu.com/geocoder?'+urllib.urlencode(metas)+'&output=json'\n",
 74 |     "    unicode_s=urllib2.urlopen(url)\n",
 75 |     "    \n",
 76 |     "    return json.loads(unicode_s.read())\n",
 77 |     "\n",
 78 |     "city_meta_lis=[]  #  计算 geohash 编码并存储\n",
 79 |     "for city in city_lis:\n",
 80 |     "    tmp=get_metas_from_baidu(city)\n",
 81 |     "    latitude=tmp['result']['location']['lat']\n",
 82 |     "    longitude=tmp['result']['location']['lng']\n",
 83 |     "    t_geohash=mzgeohash.encode((longitude,latitude)) # 使用mzgeohash 计算geohash\n",
 84 |     "    city_meta_lis.append([city,latitude,longitude,t_geohash]) # 存储"
 85 |    ]
 86 |   },
 87 |   {
 88 |    "cell_type": "code",
 89 |    "execution_count": 24,
 90 |    "metadata": {},
 91 |    "outputs": [
 92 |     {
 93 |      "data": {
 94 |       "text/html": [
 95 |        "<div>\n",
 96 |        "<style>\n",
 97 |        "    .dataframe thead tr:only-child th {\n",
 98 |        "        text-align: right;\n",
 99 |        "    }\n",
100 |        "\n",
101 |        "    .dataframe thead th {\n",
102 |        "        text-align: left;\n",
103 |        "    }\n",
104 |        "\n",
105 |        "    .dataframe tbody tr th {\n",
106 |        "        vertical-align: top;\n",
107 |        "    }\n",
108 |        "</style>\n",
109 |        "<table border=\"1\" class=\"dataframe\">\n",
110 |        "  <thead>\n",
111 |        "    <tr style=\"text-align: right;\">\n",
112 |        "      <th></th>\n",
113 |        "      <th>city</th>\n",
114 |        "      <th>latitude</th>\n",
115 |        "      <th>longitude</th>\n",
116 |        "      <th>geohash</th>\n",
117 |        "    </tr>\n",
118 |        "  </thead>\n",
119 |        "  <tbody>\n",
120 |        "    <tr>\n",
121 |        "      <th>0</th>\n",
122 |        "      <td>北京</td>\n",
123 |        "      <td>39.929986</td>\n",
124 |        "      <td>116.395645</td>\n",
125 |        "      <td>wx4g0th9p0gk</td>\n",
126 |        "    </tr>\n",
127 |        "    <tr>\n",
128 |        "      <th>1</th>\n",
129 |        "      <td>上海</td>\n",
130 |        "      <td>31.249162</td>\n",
131 |        "      <td>121.487899</td>\n",
132 |        "      <td>wtw3u88z94p0</td>\n",
133 |        "    </tr>\n",
134 |        "    <tr>\n",
135 |        "      <th>2</th>\n",
136 |        "      <td>郑州</td>\n",
137 |        "      <td>34.756610</td>\n",
138 |        "      <td>113.649644</td>\n",
139 |        "      <td>ww0vdpjputsw</td>\n",
140 |        "    </tr>\n",
141 |        "  </tbody>\n",
142 |        "</table>\n",
143 |        "</div>"
144 |       ],
145 |       "text/plain": [
146 |        "  city   latitude   longitude       geohash\n",
147 |        "0   北京  39.929986  116.395645  wx4g0th9p0gk\n",
148 |        "1   上海  31.249162  121.487899  wtw3u88z94p0\n",
149 |        "2   郑州  34.756610  113.649644  ww0vdpjputsw"
150 |       ]
151 |      },
152 |      "execution_count": 24,
153 |      "metadata": {},
154 |      "output_type": "execute_result"
155 |     }
156 |    ],
157 |    "source": [
158 |     "# 格式化输出\n",
159 |     "df=pd.DataFrame(city_meta_lis, columns=['city','latitude','longitude','geohash'])\n",
160 |     "df"
161 |    ]
162 |   },
163 |   {
164 |    "cell_type": "markdown",
165 |    "metadata": {},
166 |    "source": [
167 |     "### mzgeohash\n",
168 |     "- 调用方式\n",
169 |     "- 实现原理"
170 |    ]
171 |   },
172 |   {
173 |    "cell_type": "markdown",
174 |    "metadata": {},
175 |    "source": [
176 |     "### list all member methods"
177 |    ]
178 |   },
179 |   {
180 |    "cell_type": "code",
181 |    "execution_count": 23,
182 |    "metadata": {},
183 |    "outputs": [
184 |     {
185 |      "data": {
186 |       "text/plain": [
187 |        "['__builtins__',\n",
188 |        " '__doc__',\n",
189 |        " '__file__',\n",
190 |        " '__name__',\n",
191 |        " '__package__',\n",
192 |        " '__path__',\n",
193 |        " '__version__',\n",
194 |        " 'adjacent',\n",
195 |        " 'decode',\n",
196 |        " 'encode',\n",
197 |        " 'geohash',\n",
198 |        " 'neighbors',\n",
199 |        " 'neighborsfit']"
200 |       ]
201 |      },
202 |      "execution_count": 23,
203 |      "metadata": {},
204 |      "output_type": "execute_result"
205 |     }
206 |    ],
207 |    "source": [
208 |     "dir(mzgeohash)"
209 |    ]
210 |   },
211 |   {
212 |    "cell_type": "markdown",
213 |    "metadata": {},
214 |    "source": [
215 |     "#### 经纬度 转换为 geohash"
216 |    ]
217 |   },
218 |   {
219 |    "cell_type": "code",
220 |    "execution_count": 31,
221 |    "metadata": {},
222 |    "outputs": [
223 |     {
224 |      "data": {
225 |       "text/plain": [
226 |        "'xn76urwe1g9y'"
227 |       ]
228 |      },
229 |      "execution_count": 31,
230 |      "metadata": {},
231 |      "output_type": "execute_result"
232 |     }
233 |    ],
234 |    "source": [
235 |     "mzgeohash.encode([139.76608408614993, 35.681382017210126])"
236 |    ]
237 |   },
238 |   {
239 |    "cell_type": "markdown",
240 |    "metadata": {},
241 |    "source": [
242 |     "#### geohash 转换为 经纬度"
243 |    ]
244 |   },
245 |   {
246 |    "cell_type": "code",
247 |    "execution_count": 33,
248 |    "metadata": {},
249 |    "outputs": [
250 |     {
251 |      "data": {
252 |       "text/plain": [
253 |        "(139.76608408614993, 35.681382017210126)"
254 |       ]
255 |      },
256 |      "execution_count": 33,
257 |      "metadata": {},
258 |      "output_type": "execute_result"
259 |     }
260 |    ],
261 |    "source": [
262 |     "mzgeohash.decode('xn76urwe1g9y')"
263 |    ]
264 |   },
265 |   {
266 |    "cell_type": "markdown",
267 |    "metadata": {},
268 |    "source": [
269 |     "#### 已知 geohash ，计算某一方向的临近geohash\n",
270 |     "- 参数 1\n",
271 |     "    - 已知 geohash 串\n",
272 |     "- 参数 2\n",
273 |     "    - 方向"
274 |    ]
275 |   },
276 |   {
277 |    "cell_type": "code",
278 |    "execution_count": 35,
279 |    "metadata": {},
280 |    "outputs": [
281 |     {
282 |      "data": {
283 |       "text/plain": [
284 |        "'xn76urwe1g9z'"
285 |       ]
286 |      },
287 |      "execution_count": 35,
288 |      "metadata": {},
289 |      "output_type": "execute_result"
290 |     }
291 |    ],
292 |    "source": [
293 |     "mzgeohash.adjacent('xn76urwe1g9y','n') # "
294 |    ]
295 |   },
296 |   {
297 |    "cell_type": "markdown",
298 |    "metadata": {},
299 |    "source": [
300 |     "#### 已知 geohash ，临近geohash\n",
301 |     "- 九宫格，即周围 8 个geohash"
302 |    ]
303 |   },
304 |   {
305 |    "cell_type": "code",
306 |    "execution_count": 34,
307 |    "metadata": {},
308 |    "outputs": [
309 |     {
310 |      "data": {
311 |       "text/plain": [
312 |        "{'c': 'xn76urwe1g9y',\n",
313 |        " 'e': 'xn76urwe1gdn',\n",
314 |        " 'n': 'xn76urwe1g9z',\n",
315 |        " 'ne': 'xn76urwe1gdp',\n",
316 |        " 'nw': 'xn76urwe1g9x',\n",
317 |        " 's': 'xn76urwe1g9v',\n",
318 |        " 'se': 'xn76urwe1gdj',\n",
319 |        " 'sw': 'xn76urwe1g9t',\n",
320 |        " 'w': 'xn76urwe1g9w'}"
321 |       ]
322 |      },
323 |      "execution_count": 34,
324 |      "metadata": {},
325 |      "output_type": "execute_result"
326 |     }
327 |    ],
328 |    "source": [
329 |     "mzgeohash.neighbors('xn76urwe1g9y')"
330 |    ]
331 |   },
332 |   {
333 |    "cell_type": "markdown",
334 |    "metadata": {},
335 |    "source": [
336 |     "#### 已知 某位置点经纬度和周围经纬度点集，计算同属 geohash"
337 |    ]
338 |   },
339 |   {
340 |    "cell_type": "code",
341 |    "execution_count": 37,
342 |    "metadata": {},
343 |    "outputs": [
344 |     {
345 |      "data": {
346 |       "text/plain": [
347 |        "'9q9'"
348 |       ]
349 |      },
350 |      "execution_count": 37,
351 |      "metadata": {},
352 |      "output_type": "execute_result"
353 |     }
354 |    ],
355 |    "source": [
356 |     "test_centroid = [-122.18472385000001, 37.7881345]\n",
357 |     "test_points = [\n",
358 |     "(-122.2992715, 37.9030588),\n",
359 |     "(-122.396742, 37.792976),\n",
360 |     "(-122.4474142, 37.72198087),\n",
361 |     "(-121.9764, 37.557355),\n",
362 |     "(-122.029095, 37.973737),\n",
363 |     "(-122.224274, 37.774963),\n",
364 |     "(-122.271604, 37.803664),\n",
365 |     "(-122.126871, 37.697185),\n",
366 |     "(-122.087967, 37.670399),\n",
367 |     "(-122.123801, 37.893394),\n",
368 |     "(-122.269029, 37.80787),\n",
369 |     "(-122.265609, 37.797484),\n",
370 |     "(-122.267227, 37.828415),\n",
371 |     "(-122.067423, 37.905628),\n",
372 |     "(-122.267227, 37.828415),\n",
373 |     "(-122.38666, 37.599787),\n",
374 |     "(-122.075567, 37.690754),\n",
375 |     "(-122.401407, 37.789256),\n",
376 |     "(-122.283451, 37.87404),\n",
377 |     "(-122.269029, 37.80787),\n",
378 |     "(-122.1837911, 37.87836087),\n",
379 |     "(-122.419694, 37.765062),\n",
380 |     "(-122.2945822, 37.80467476),\n",
381 |     "(-122.21244024, 37.71297174),\n",
382 |     "(-121.945154, 38.018914),\n",
383 |     "(-122.466233, 37.684638),\n",
384 |     "(-122.056013, 37.928403),\n",
385 |     "(-122.406857, 37.784991),\n",
386 |     "(-122.418466, 37.752254),\n",
387 |     "(-122.26978, 37.853024),\n",
388 |     "(-122.251793, 37.844601),\n",
389 |     "(-121.928099, 37.699759),\n",
390 |     "(-122.416038, 37.637753),\n",
391 |     "(-122.1613112, 37.72261921),\n",
392 |     "(-122.0575506, 37.63479954),\n",
393 |     "(-122.392612, 37.616035),\n",
394 |     "(-122.413756, 37.779528),\n",
395 |     "(-122.353165, 37.936887),\n",
396 |     "(-122.197273, 37.754006),\n",
397 |     "(-122.017867, 37.591208),\n",
398 |     "(-122.024597, 38.003275),\n",
399 |     "(-122.4690807, 37.70612055),\n",
400 |     "(-122.268045, 37.869867),\n",
401 |     "(-122.444116, 37.664174),\n",
402 |     "(-121.900367, 37.701695),\n",
403 |     "(-122.317269, 37.925655),\n",
404 |     "(-122.434092, 37.732921)\n",
405 |     "]\n",
406 |     "\n",
407 |     "# expect = '9q9'\n",
408 |     "mzgeohash.neighborsfit(test_centroid, test_points)"
409 |    ]
410 |   },
411 |   {
412 |    "cell_type": "markdown",
413 |    "metadata": {},
414 |    "source": [
415 |     "### 使用unittest进行 mzgeohash 模块测试\n",
416 |     "- 通过 testsuit 执行测试用例\n",
417 |     "- TestCase：所有测试用例的基本类，给定测试方法的名称，返回测试用例实例；\n",
418 |     "- TestSuit：组织测试用例的实例，支持测试用例的添加和删除，最终将传递给 testRunner进行测试执行；\n",
419 |     "- TextTestRunner：进行测试用例执行的实例，其中Text的意思是以文本形式显示测试结果。\n",
420 |     "    - 测试结果保存在 TextTestResult 实例中，包括运行多少测试用例，成功多少，失败多少等信息；"
421 |    ]
422 |   },
423 |   {
424 |    "cell_type": "code",
425 |    "execution_count": 6,
426 |    "metadata": {
427 |     "collapsed": true
428 |    },
429 |    "outputs": [],
430 |    "source": [
431 |     "import unittest\n",
432 |     "from mzgeohash.test_geohash import Test_encode_decode\n",
433 |     "from mzgeohash.test_geohash import Test_adjacent\n",
434 |     "from mzgeohash.test_geohash import Test_neighbors\n",
435 |     "from mzgeohash.test_geohash import Test_neighborsfit"
436 |    ]
437 |   },
438 |   {
439 |    "cell_type": "code",
440 |    "execution_count": 35,
441 |    "metadata": {},
442 |    "outputs": [
443 |     {
444 |      "name": "stderr",
445 |      "output_type": "stream",
446 |      "text": [
447 |       "............\n",
448 |       "----------------------------------------------------------------------\n",
449 |       "Ran 12 tests in 0.053s\n",
450 |       "\n",
451 |       "OK\n"
452 |      ]
453 |     }
454 |    ],
455 |    "source": [
456 |     "suite=unittest.TestSuite()\n",
457 |     "suite.addTest(Test_encode_decode('test_decode'))\n",
458 |     "suite.addTest(Test_encode_decode('test_encode'))\n",
459 |     "suite.addTest(Test_encode_decode('test_roundtrip'))\n",
460 |     "suite.addTest(Test_neighbors('test_neighbors'))\n",
461 |     "suite.addTest(Test_adjacent('test_adjacent'))\n",
462 |     "suite.addTest(Test_neighborsfit('test_neighborsfit'))\n",
463 |     "\n",
464 |     "runner=unittest.TextTestRunner()\n",
465 |     "runner.run(suite);"
466 |    ]
467 |   }
468 |  ],
469 |  "metadata": {
470 |   "kernelspec": {
471 |    "display_name": "Python 2",
472 |    "language": "python",
473 |    "name": "python2"
474 |   },
475 |   "language_info": {
476 |    "codemirror_mode": {
477 |     "name": "ipython",
478 |     "version": 2
479 |    },
480 |    "file_extension": ".py",
481 |    "mimetype": "text/x-python",
482 |    "name": "python",
483 |    "nbconvert_exporter": "python",
484 |    "pygments_lexer": "ipython2",
485 |    "version": "2.7.13"
486 |   },
487 |   "toc": {
488 |    "nav_menu": {},
489 |    "number_sections": true,
490 |    "sideBar": true,
491 |    "skip_h1_title": false,
492 |    "toc_cell": false,
493 |    "toc_position": {
494 |     "height": "595px",
495 |     "left": "0px",
496 |     "right": "1092px",
497 |     "top": "107px",
498 |     "width": "212px"
499 |    },
500 |    "toc_section_display": "block",
501 |    "toc_window_display": true
502 |   }
503 |  },
504 |  "nbformat": 4,
505 |  "nbformat_minor": 2
506 | }
507 | 


--------------------------------------------------------------------------------
/post_metas.csv:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Kdotm/Python_Series/c686d48797b7266934958b09247aa3ffe783c026/post_metas.csv


--------------------------------------------------------------------------------
/spider_huatu_civil_servant_post_metas.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {
  6 |     "deletable": true,
  7 |     "editable": true
  8 |    },
  9 |    "source": [
 10 |     "### 爬取浙江公务员职位信息"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "metadata": {
 17 |     "collapsed": true,
 18 |     "deletable": true,
 19 |     "editable": true
 20 |    },
 21 |    "outputs": [],
 22 |    "source": [
 23 |     "import urllib\n",
 24 |     "import pandas as pd\n",
 25 |     "\n",
 26 |     "from bs4 import BeautifulSoup"
 27 |    ]
 28 |   },
 29 |   {
 30 |    "cell_type": "markdown",
 31 |    "metadata": {},
 32 |    "source": [
 33 |     "### 1 爬取页面"
 34 |    ]
 35 |   },
 36 |   {
 37 |    "cell_type": "code",
 38 |    "execution_count": 3,
 39 |    "metadata": {
 40 |     "collapsed": false,
 41 |     "deletable": true,
 42 |     "editable": true
 43 |    },
 44 |    "outputs": [],
 45 |    "source": [
 46 |     "api = 'http://zw.huatu.com'\n",
 47 |     "base='/2018/'\n",
 48 |     "url=api+base\n",
 49 |     "\n",
 50 |     "header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3236.0 Safari/537.36'}\n",
 51 |     "request = urllib.request.Request(url,headers=header)\n",
 52 |     "response = urllib.request.urlopen(request).read()\n",
 53 |     "\n",
 54 |     "content=BeautifulSoup(response, 'lxml')"
 55 |    ]
 56 |   },
 57 |   {
 58 |    "cell_type": "markdown",
 59 |    "metadata": {},
 60 |    "source": [
 61 |     "### 2 内容解析\n",
 62 |     "- 省/市 : 对应 URL [32个]"
 63 |    ]
 64 |   },
 65 |   {
 66 |    "cell_type": "code",
 67 |    "execution_count": 5,
 68 |    "metadata": {
 69 |     "collapsed": false,
 70 |     "deletable": true,
 71 |     "editable": true
 72 |    },
 73 |    "outputs": [],
 74 |    "source": [
 75 |     "areas_txt=content.find_all('p', attrs={'id':'ydiqu'})[0]\n",
 76 |     "area_metas_lis=[]\n",
 77 |     "counter=0\n",
 78 |     "\n",
 79 |     "for i in areas_txt.find_all('a', attrs={'target':'_blank'}):\n",
 80 |     "    url=api+i.get_attribute_list('href')[0][2:]\n",
 81 |     "    area=i.get_text()\n",
 82 |     "    counter+=1\n",
 83 |     "    area_metas_lis.append([counter,area,url])"
 84 |    ]
 85 |   },
 86 |   {
 87 |    "cell_type": "code",
 88 |    "execution_count": 12,
 89 |    "metadata": {
 90 |     "collapsed": false,
 91 |     "deletable": true,
 92 |     "editable": true
 93 |    },
 94 |    "outputs": [
 95 |     {
 96 |      "data": {
 97 |       "text/html": [
 98 |        "<div>\n",
 99 |        "<style>\n",
100 |        "    .dataframe thead tr:only-child th {\n",
101 |        "        text-align: right;\n",
102 |        "    }\n",
103 |        "\n",
104 |        "    .dataframe thead th {\n",
105 |        "        text-align: left;\n",
106 |        "    }\n",
107 |        "\n",
108 |        "    .dataframe tbody tr th {\n",
109 |        "        vertical-align: top;\n",
110 |        "    }\n",
111 |        "</style>\n",
112 |        "<table border=\"1\" class=\"dataframe\">\n",
113 |        "  <thead>\n",
114 |        "    <tr style=\"text-align: right;\">\n",
115 |        "      <th></th>\n",
116 |        "      <th>no</th>\n",
117 |        "      <th>area</th>\n",
118 |        "      <th>url</th>\n",
119 |        "    </tr>\n",
120 |        "  </thead>\n",
121 |        "  <tbody>\n",
122 |        "    <tr>\n",
123 |        "      <th>0</th>\n",
124 |        "      <td>1</td>\n",
125 |        "      <td>安徽</td>\n",
126 |        "      <td>http://zw.huatu.com/2018/buweisearch/1.html</td>\n",
127 |        "    </tr>\n",
128 |        "    <tr>\n",
129 |        "      <th>1</th>\n",
130 |        "      <td>2</td>\n",
131 |        "      <td>北京</td>\n",
132 |        "      <td>http://zw.huatu.com/2018/buweisearch/2.html</td>\n",
133 |        "    </tr>\n",
134 |        "    <tr>\n",
135 |        "      <th>2</th>\n",
136 |        "      <td>3</td>\n",
137 |        "      <td>福建</td>\n",
138 |        "      <td>http://zw.huatu.com/2018/buweisearch/3.html</td>\n",
139 |        "    </tr>\n",
140 |        "    <tr>\n",
141 |        "      <th>3</th>\n",
142 |        "      <td>4</td>\n",
143 |        "      <td>甘肃</td>\n",
144 |        "      <td>http://zw.huatu.com/2018/buweisearch/4.html</td>\n",
145 |        "    </tr>\n",
146 |        "    <tr>\n",
147 |        "      <th>4</th>\n",
148 |        "      <td>5</td>\n",
149 |        "      <td>广东</td>\n",
150 |        "      <td>http://zw.huatu.com/2018/buweisearch/5.html</td>\n",
151 |        "    </tr>\n",
152 |        "  </tbody>\n",
153 |        "</table>\n",
154 |        "</div>"
155 |       ],
156 |       "text/plain": [
157 |        "   no area                                          url\n",
158 |        "0   1   安徽  http://zw.huatu.com/2018/buweisearch/1.html\n",
159 |        "1   2   北京  http://zw.huatu.com/2018/buweisearch/2.html\n",
160 |        "2   3   福建  http://zw.huatu.com/2018/buweisearch/3.html\n",
161 |        "3   4   甘肃  http://zw.huatu.com/2018/buweisearch/4.html\n",
162 |        "4   5   广东  http://zw.huatu.com/2018/buweisearch/5.html"
163 |       ]
164 |      },
165 |      "execution_count": 12,
166 |      "metadata": {},
167 |      "output_type": "execute_result"
168 |     }
169 |    ],
170 |    "source": [
171 |     "df=pd.DataFrame(area_metas_lis, columns=['no','area', 'url'])\n",
172 |     "df.head()"
173 |    ]
174 |   },
175 |   {
176 |    "cell_type": "markdown",
177 |    "metadata": {
178 |     "deletable": true,
179 |     "editable": true
180 |    },
181 |    "source": [
182 |     "### 3 以浙江为例，通过省份查询招聘单位及具体信息访问途径（URL）"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": 8,
188 |    "metadata": {
189 |     "collapsed": false,
190 |     "deletable": true,
191 |     "editable": true
192 |    },
193 |    "outputs": [
194 |     {
195 |      "data": {
196 |       "text/html": [
197 |        "<div>\n",
198 |        "<style>\n",
199 |        "    .dataframe thead tr:only-child th {\n",
200 |        "        text-align: right;\n",
201 |        "    }\n",
202 |        "\n",
203 |        "    .dataframe thead th {\n",
204 |        "        text-align: left;\n",
205 |        "    }\n",
206 |        "\n",
207 |        "    .dataframe tbody tr th {\n",
208 |        "        vertical-align: top;\n",
209 |        "    }\n",
210 |        "</style>\n",
211 |        "<table border=\"1\" class=\"dataframe\">\n",
212 |        "  <thead>\n",
213 |        "    <tr style=\"text-align: right;\">\n",
214 |        "      <th></th>\n",
215 |        "      <th>no</th>\n",
216 |        "      <th>area</th>\n",
217 |        "      <th>url</th>\n",
218 |        "    </tr>\n",
219 |        "  </thead>\n",
220 |        "  <tbody>\n",
221 |        "    <tr>\n",
222 |        "      <th>30</th>\n",
223 |        "      <td>31</td>\n",
224 |        "      <td>浙江</td>\n",
225 |        "      <td>http://zw.huatu.com/2018/buweisearch/31.html</td>\n",
226 |        "    </tr>\n",
227 |        "  </tbody>\n",
228 |        "</table>\n",
229 |        "</div>"
230 |       ],
231 |       "text/plain": [
232 |        "    no area                                           url\n",
233 |        "30  31   浙江  http://zw.huatu.com/2018/buweisearch/31.html"
234 |       ]
235 |      },
236 |      "execution_count": 8,
237 |      "metadata": {},
238 |      "output_type": "execute_result"
239 |     }
240 |    ],
241 |    "source": [
242 |     "query_area='浙江'\n",
243 |     "df[df.area==query_area]"
244 |    ]
245 |   },
246 |   {
247 |    "cell_type": "code",
248 |    "execution_count": 9,
249 |    "metadata": {
250 |     "collapsed": false,
251 |     "deletable": true,
252 |     "editable": true
253 |    },
254 |    "outputs": [],
255 |    "source": [
256 |     "url2=df[df.area==query_area].url.values[0]\n",
257 |     "\n",
258 |     "request2 = urllib.request.Request(url2,headers=header)\n",
259 |     "response2 = urllib.request.urlopen(request2).read()\n",
260 |     "content2=BeautifulSoup(response2, 'lxml')\n",
261 |     "\n",
262 |     "tmp2=content2.find_all('table', attrs={'cellspacing':'0','width':'100%'})[0]\n",
263 |     "\n",
264 |     "unit_lis=[] # 存储职位列表\n",
265 |     "for i in tmp2.find_all('a'):\n",
266 |     "    t_url=api+'/2018'+i.get_attribute_list('href')[0][2:]\n",
267 |     "    unit_lis.append([i.get_text().strip(),t_url]) # strip 去除空格\n",
268 |     "\n",
269 |     "unit_df=pd.DataFrame(unit_lis,columns=['unit_name','url'])"
270 |    ]
271 |   },
272 |   {
273 |    "cell_type": "code",
274 |    "execution_count": 13,
275 |    "metadata": {
276 |     "collapsed": false,
277 |     "deletable": true,
278 |     "editable": true,
279 |     "scrolled": false
280 |    },
281 |    "outputs": [
282 |     {
283 |      "data": {
284 |       "text/html": [
285 |        "<div>\n",
286 |        "<style>\n",
287 |        "    .dataframe thead tr:only-child th {\n",
288 |        "        text-align: right;\n",
289 |        "    }\n",
290 |        "\n",
291 |        "    .dataframe thead th {\n",
292 |        "        text-align: left;\n",
293 |        "    }\n",
294 |        "\n",
295 |        "    .dataframe tbody tr th {\n",
296 |        "        vertical-align: top;\n",
297 |        "    }\n",
298 |        "</style>\n",
299 |        "<table border=\"1\" class=\"dataframe\">\n",
300 |        "  <thead>\n",
301 |        "    <tr style=\"text-align: right;\">\n",
302 |        "      <th></th>\n",
303 |        "      <th>unit_name</th>\n",
304 |        "      <th>url</th>\n",
305 |        "    </tr>\n",
306 |        "  </thead>\n",
307 |        "  <tbody>\n",
308 |        "    <tr>\n",
309 |        "      <th>0</th>\n",
310 |        "      <td>国家物资储备局浙江办事处</td>\n",
311 |        "      <td>http://zw.huatu.com/2018/buwei2018/1763.html</td>\n",
312 |        "    </tr>\n",
313 |        "    <tr>\n",
314 |        "      <th>1</th>\n",
315 |        "      <td>浙江海事局</td>\n",
316 |        "      <td>http://zw.huatu.com/2018/buwei2018/2009.html</td>\n",
317 |        "    </tr>\n",
318 |        "    <tr>\n",
319 |        "      <th>2</th>\n",
320 |        "      <td>杭州海关</td>\n",
321 |        "      <td>http://zw.huatu.com/2018/buwei2018/2105.html</td>\n",
322 |        "    </tr>\n",
323 |        "    <tr>\n",
324 |        "      <th>3</th>\n",
325 |        "      <td>宁波海关</td>\n",
326 |        "      <td>http://zw.huatu.com/2018/buwei2018/2107.html</td>\n",
327 |        "    </tr>\n",
328 |        "    <tr>\n",
329 |        "      <th>4</th>\n",
330 |        "      <td>浙江省国家税务局</td>\n",
331 |        "      <td>http://zw.huatu.com/2018/buwei2018/2175.html</td>\n",
332 |        "    </tr>\n",
333 |        "  </tbody>\n",
334 |        "</table>\n",
335 |        "</div>"
336 |       ],
337 |       "text/plain": [
338 |        "      unit_name                                           url\n",
339 |        "0  国家物资储备局浙江办事处  http://zw.huatu.com/2018/buwei2018/1763.html\n",
340 |        "1         浙江海事局  http://zw.huatu.com/2018/buwei2018/2009.html\n",
341 |        "2          杭州海关  http://zw.huatu.com/2018/buwei2018/2105.html\n",
342 |        "3          宁波海关  http://zw.huatu.com/2018/buwei2018/2107.html\n",
343 |        "4      浙江省国家税务局  http://zw.huatu.com/2018/buwei2018/2175.html"
344 |       ]
345 |      },
346 |      "execution_count": 13,
347 |      "metadata": {},
348 |      "output_type": "execute_result"
349 |     }
350 |    ],
351 |    "source": [
352 |     "unit_df.head()"
353 |    ]
354 |   },
355 |   {
356 |    "cell_type": "markdown",
357 |    "metadata": {
358 |     "deletable": true,
359 |     "editable": true
360 |    },
361 |    "source": [
362 |     "### 4 查询所有部门的招聘岗位等详细信息"
363 |    ]
364 |   },
365 |   {
366 |    "cell_type": "code",
367 |    "execution_count": 10,
368 |    "metadata": {
369 |     "collapsed": true,
370 |     "deletable": true,
371 |     "editable": true
372 |    },
373 |    "outputs": [],
374 |    "source": [
375 |     "'''\n",
376 |     "获取岗位详细信息\n",
377 |     "url :\n",
378 |     "    访问路径\n",
379 |     "'''\n",
380 |     "def get_post_metas(url):\n",
381 |     "    tmp_request = urllib.request.Request(url,headers=header)\n",
382 |     "    tmp_response = urllib.request.urlopen(tmp_request).read()\n",
383 |     "    tmp_content=BeautifulSoup(tmp_response, 'lxml')\n",
384 |     "    \n",
385 |     "    td_lis=[i.get_text() for i in tmp_content.find_all('td')]\n",
386 |     "    internal=[]\n",
387 |     "    for i in range(len(td_lis)):\n",
388 |     "        if i%10==0: # 生成间隔区间\n",
389 |     "            internal.append([i,i+10])\n",
390 |     "    \n",
391 |     "    row_lis=[]\n",
392 |     "    for lt,rt in internal: # 根据间隔区间，将数据分行\n",
393 |     "        row_lis.append(td_lis[lt:rt])\n",
394 |     "        \n",
395 |     "    return row_lis\n",
396 |     "\n",
397 |     "post_metas_lis=[]\n",
398 |     "\n",
399 |     "for unit_name,url in unit_lis: # 循环，加工招聘单位所招岗位详细信息\n",
400 |     "    post_metas_lis+=get_post_metas(url)\n",
401 |     "\n",
402 |     "# 将 list 转换为 DataFrame 格式\n",
403 |     "\n",
404 |     "# '部门名称','用人用司','职位名称','要求专业','招考人数','报考人数','历年分数线','历年竞争比','录取概率','对比'\n",
405 |     "post_metas_df=pd.DataFrame(post_metas_lis, columns=['unit_name','employee_unit','post_name','professional','person_num','person_num2','view','view2','detail','compare'])"
406 |    ]
407 |   },
408 |   {
409 |    "cell_type": "code",
410 |    "execution_count": 22,
411 |    "metadata": {
412 |     "collapsed": false
413 |    },
414 |    "outputs": [
415 |     {
416 |      "data": {
417 |       "text/html": [
418 |        "<div>\n",
419 |        "<style>\n",
420 |        "    .dataframe thead tr:only-child th {\n",
421 |        "        text-align: right;\n",
422 |        "    }\n",
423 |        "\n",
424 |        "    .dataframe thead th {\n",
425 |        "        text-align: left;\n",
426 |        "    }\n",
427 |        "\n",
428 |        "    .dataframe tbody tr th {\n",
429 |        "        vertical-align: top;\n",
430 |        "    }\n",
431 |        "</style>\n",
432 |        "<table border=\"1\" class=\"dataframe\">\n",
433 |        "  <thead>\n",
434 |        "    <tr style=\"text-align: right;\">\n",
435 |        "      <th></th>\n",
436 |        "      <th>unit_name</th>\n",
437 |        "      <th>employee_unit</th>\n",
438 |        "      <th>post_name</th>\n",
439 |        "      <th>professional</th>\n",
440 |        "      <th>person_num</th>\n",
441 |        "      <th>person_num2</th>\n",
442 |        "      <th>view</th>\n",
443 |        "      <th>view2</th>\n",
444 |        "      <th>detail</th>\n",
445 |        "      <th>compare</th>\n",
446 |        "    </tr>\n",
447 |        "  </thead>\n",
448 |        "  <tbody>\n",
449 |        "    <tr>\n",
450 |        "      <th>100</th>\n",
451 |        "      <td>浙江省国家税务局</td>\n",
452 |        "      <td>杭州市上城区国家税务局</td>\n",
453 |        "      <td>纳税服务科科员（一）</td>\n",
454 |        "      <td>公共管理类</td>\n",
455 |        "      <td>1</td>\n",
456 |        "      <td>0</td>\n",
457 |        "      <td>查看</td>\n",
458 |        "      <td>查看</td>\n",
459 |        "      <td>详情</td>\n",
460 |        "      <td>对比</td>\n",
461 |        "    </tr>\n",
462 |        "    <tr>\n",
463 |        "      <th>101</th>\n",
464 |        "      <td>浙江省国家税务局</td>\n",
465 |        "      <td>杭州市上城区国家税务局</td>\n",
466 |        "      <td>纳税服务科科员（二）</td>\n",
467 |        "      <td>工商管理类</td>\n",
468 |        "      <td>1</td>\n",
469 |        "      <td>0</td>\n",
470 |        "      <td>查看</td>\n",
471 |        "      <td>查看</td>\n",
472 |        "      <td>详情</td>\n",
473 |        "      <td>对比</td>\n",
474 |        "    </tr>\n",
475 |        "    <tr>\n",
476 |        "      <th>102</th>\n",
477 |        "      <td>浙江省国家税务局</td>\n",
478 |        "      <td>杭州市上城区国家税务局</td>\n",
479 |        "      <td>纳税服务科科员（三）</td>\n",
480 |        "      <td>财政学类</td>\n",
481 |        "      <td>1</td>\n",
482 |        "      <td>0</td>\n",
483 |        "      <td>查看</td>\n",
484 |        "      <td>查看</td>\n",
485 |        "      <td>详情</td>\n",
486 |        "      <td>对比</td>\n",
487 |        "    </tr>\n",
488 |        "  </tbody>\n",
489 |        "</table>\n",
490 |        "</div>"
491 |       ],
492 |       "text/plain": [
493 |        "    unit_name employee_unit   post_name professional person_num person_num2  \\\n",
494 |        "100  浙江省国家税务局   杭州市上城区国家税务局  纳税服务科科员（一）        公共管理类          1           0   \n",
495 |        "101  浙江省国家税务局   杭州市上城区国家税务局  纳税服务科科员（二）        工商管理类          1           0   \n",
496 |        "102  浙江省国家税务局   杭州市上城区国家税务局  纳税服务科科员（三）         财政学类          1           0   \n",
497 |        "\n",
498 |        "    view view2 detail compare  \n",
499 |        "100   查看    查看     详情      对比  \n",
500 |        "101   查看    查看     详情      对比  \n",
501 |        "102   查看    查看     详情      对比  "
502 |       ]
503 |      },
504 |      "execution_count": 22,
505 |      "metadata": {},
506 |      "output_type": "execute_result"
507 |     }
508 |    ],
509 |    "source": [
510 |     "post_metas_df[post_metas_df.unit_name=='浙江省国家税务局'].head(3)"
511 |    ]
512 |   },
513 |   {
514 |    "cell_type": "code",
515 |    "execution_count": 249,
516 |    "metadata": {
517 |     "collapsed": true,
518 |     "deletable": true,
519 |     "editable": true
520 |    },
521 |    "outputs": [],
522 |    "source": [
523 |     "# 保存数据信息\n",
524 |     "\n",
525 |     "post_metas_df.to_csv('./post_metas.csv')"
526 |    ]
527 |   }
528 |  ],
529 |  "metadata": {
530 |   "kernelspec": {
531 |    "display_name": "Python 3",
532 |    "language": "python",
533 |    "name": "python3"
534 |   },
535 |   "language_info": {
536 |    "codemirror_mode": {
537 |     "name": "ipython",
538 |     "version": 3
539 |    },
540 |    "file_extension": ".py",
541 |    "mimetype": "text/x-python",
542 |    "name": "python",
543 |    "nbconvert_exporter": "python",
544 |    "pygments_lexer": "ipython3",
545 |    "version": "3.6.3"
546 |   }
547 |  },
548 |  "nbformat": 4,
549 |  "nbformat_minor": 2
550 | }
551 | 


--------------------------------------------------------------------------------
/spider_qiushibaike_content_datas.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "### 爬取 糗事百科段子 内容数据\n",
  8 |     "---\n",
  9 |     "- author：\n",
 10 |     "    - kngines\n",
 11 |     "- date：\n",
 12 |     "    - 20180118"
 13 |    ]
 14 |   },
 15 |   {
 16 |    "cell_type": "code",
 17 |    "execution_count": 1,
 18 |    "metadata": {
 19 |     "collapsed": false
 20 |    },
 21 |    "outputs": [],
 22 |    "source": [
 23 |     "import re\n",
 24 |     "import urllib\n",
 25 |     "import bs4\n",
 26 |     "import pandas as pd\n",
 27 |     "from bs4 import BeautifulSoup\n",
 28 |     "\n",
 29 |     "page = 1 # 第 1 页\n",
 30 |     "\n",
 31 |     "url = 'http://www.qiushibaike.com/hot/page/' + str(page)\n",
 32 |     "header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3236.0 Safari/537.36'}\n",
 33 |     "request = urllib.request.Request(url,headers=header)\n",
 34 |     "response = urllib.request.urlopen(request).read()\n",
 35 |     "\n",
 36 |     "content=BeautifulSoup(response, 'lxml')\n",
 37 |     "\n",
 38 |     "'''\n",
 39 |     "1 获取段子内容\n",
 40 |     "'''\n",
 41 |     "divs = content.find_all('div', class_='content')\n",
 42 |     "content_lis=[]\n",
 43 |     "for div in divs:\n",
 44 |     "    content_lis.append(div.span.get_text())\n",
 45 |     "\n",
 46 |     "'''\n",
 47 |     "2 获取用户昵称\n",
 48 |     "''' \n",
 49 |     "tmp=content.find_all('div', class_='col1')[0]\n",
 50 |     "nick_name_lis=[]\n",
 51 |     "for nick_name in tmp.find_all('h2'):\n",
 52 |     "    nick_name_lis.append(nick_name.get_text())\n",
 53 |     "\n",
 54 |     "'''\n",
 55 |     "3 获取好笑、评论数量\n",
 56 |     "'''\n",
 57 |     "counter=0\n",
 58 |     "funny_lis=[]\n",
 59 |     "comment_lis=[]\n",
 60 |     "for cofu in content.find_all('i', class_='number'):\n",
 61 |     "    counter+=1\n",
 62 |     "    if counter%2!=0:\n",
 63 |     "        funny_lis.append(cofu.get_text())\n",
 64 |     "    else :\n",
 65 |     "        comment_lis.append(cofu.get_text())       "
 66 |    ]
 67 |   },
 68 |   {
 69 |    "cell_type": "markdown",
 70 |    "metadata": {},
 71 |    "source": [
 72 |     "### 1 当前页码信息\n",
 73 |     "- 第 1 页\n",
 74 |     "    - 通过简单调整，可以实现批量爬取数据"
 75 |    ]
 76 |   },
 77 |   {
 78 |    "cell_type": "code",
 79 |    "execution_count": 2,
 80 |    "metadata": {
 81 |     "collapsed": false
 82 |    },
 83 |    "outputs": [
 84 |     {
 85 |      "name": "stdout",
 86 |      "output_type": "stream",
 87 |      "text": [
 88 |       "\u001b[1;31m[24H] current page:\u001b[0m \u001b[0;30;43m1\u001b[0m\n"
 89 |      ]
 90 |     }
 91 |    ],
 92 |    "source": [
 93 |     "current_page=content.find_all('ul',class_='pagination')[0].find_all('span',class_='current')[0].get_text()\n",
 94 |     "print ('\\033[1;31m[24H] current page:\\033[0m \\033[0;30;43m%s\\033[0m' % (current_page.replace('\\n','')))"
 95 |    ]
 96 |   },
 97 |   {
 98 |    "cell_type": "markdown",
 99 |    "metadata": {},
100 |    "source": [
101 |     "### 2 转换[DataFrame]并显示"
102 |    ]
103 |   },
104 |   {
105 |    "cell_type": "code",
106 |    "execution_count": 3,
107 |    "metadata": {
108 |     "collapsed": false
109 |    },
110 |    "outputs": [],
111 |    "source": [
112 |     "tdf=pd.DataFrame([nick_name_lis,content_lis,funny_lis,comment_lis])\n",
113 |     "df=tdf.T\n",
114 |     "df.columns=['nick_name','content','funny_cnt','comment_cnt']"
115 |    ]
116 |   },
117 |   {
118 |    "cell_type": "code",
119 |    "execution_count": 4,
120 |    "metadata": {
121 |     "collapsed": false
122 |    },
123 |    "outputs": [
124 |     {
125 |      "data": {
126 |       "text/html": [
127 |        "<div>\n",
128 |        "<style>\n",
129 |        "    .dataframe thead tr:only-child th {\n",
130 |        "        text-align: right;\n",
131 |        "    }\n",
132 |        "\n",
133 |        "    .dataframe thead th {\n",
134 |        "        text-align: left;\n",
135 |        "    }\n",
136 |        "\n",
137 |        "    .dataframe tbody tr th {\n",
138 |        "        vertical-align: top;\n",
139 |        "    }\n",
140 |        "</style>\n",
141 |        "<table border=\"1\" class=\"dataframe\">\n",
142 |        "  <thead>\n",
143 |        "    <tr style=\"text-align: right;\">\n",
144 |        "      <th></th>\n",
145 |        "      <th>nick_name</th>\n",
146 |        "      <th>content</th>\n",
147 |        "      <th>funny_cnt</th>\n",
148 |        "      <th>comment_cnt</th>\n",
149 |        "    </tr>\n",
150 |        "  </thead>\n",
151 |        "  <tbody>\n",
152 |        "    <tr>\n",
153 |        "      <th>0</th>\n",
154 |        "      <td>\\n我家熊孩子不熊\\n</td>\n",
155 |        "      <td>\\n\\n\\n九月份闺蜜来我家吃晚饭。她在用减肥瘦瘦包，这个3600块钱的瘦瘦包要求三个月内晚...</td>\n",
156 |        "      <td>758</td>\n",
157 |        "      <td>56</td>\n",
158 |        "    </tr>\n",
159 |        "    <tr>\n",
160 |        "      <th>1</th>\n",
161 |        "      <td>\\n道士下山会女神\\n</td>\n",
162 |        "      <td>\\n\\n\\n银行办点事，小侄跟着去玩，见大堂圣诞树上挂满红包，小孩好奇心重，便挨个去拆开看，...</td>\n",
163 |        "      <td>807</td>\n",
164 |        "      <td>11</td>\n",
165 |        "    </tr>\n",
166 |        "    <tr>\n",
167 |        "      <th>2</th>\n",
168 |        "      <td>\\n阿丹阿乐\\n</td>\n",
169 |        "      <td>\\n\\n\\n今天我去医院，遇到一位女士，机缘巧合比较聊得来，她说她是来做人工授精的。刚好我是...</td>\n",
170 |        "      <td>1457</td>\n",
171 |        "      <td>28</td>\n",
172 |        "    </tr>\n",
173 |        "  </tbody>\n",
174 |        "</table>\n",
175 |        "</div>"
176 |       ],
177 |       "text/plain": [
178 |        "     nick_name                                            content funny_cnt  \\\n",
179 |        "0  \\n我家熊孩子不熊\\n  \\n\\n\\n九月份闺蜜来我家吃晚饭。她在用减肥瘦瘦包，这个3600块钱的瘦瘦包要求三个月内晚...       758   \n",
180 |        "1  \\n道士下山会女神\\n  \\n\\n\\n银行办点事，小侄跟着去玩，见大堂圣诞树上挂满红包，小孩好奇心重，便挨个去拆开看，...       807   \n",
181 |        "2     \\n阿丹阿乐\\n  \\n\\n\\n今天我去医院，遇到一位女士，机缘巧合比较聊得来，她说她是来做人工授精的。刚好我是...      1457   \n",
182 |        "\n",
183 |        "  comment_cnt  \n",
184 |        "0          56  \n",
185 |        "1          11  \n",
186 |        "2          28  "
187 |       ]
188 |      },
189 |      "execution_count": 4,
190 |      "metadata": {},
191 |      "output_type": "execute_result"
192 |     }
193 |    ],
194 |    "source": [
195 |     "df.head(3)"
196 |    ]
197 |   },
198 |   {
199 |    "cell_type": "markdown",
200 |    "metadata": {},
201 |    "source": [
202 |     "### 3 格式化显示数据"
203 |    ]
204 |   },
205 |   {
206 |    "cell_type": "code",
207 |    "execution_count": 5,
208 |    "metadata": {
209 |     "collapsed": false
210 |    },
211 |    "outputs": [],
212 |    "source": [
213 |     "pd.set_option('display.width',200)\n",
214 |     "pd.set_option('display.max_columns',20)\n",
215 |     "pd.set_option('display.max_rows',50)\n",
216 |     "pd.set_option('display.max_colwidth',200)"
217 |    ]
218 |   },
219 |   {
220 |    "cell_type": "code",
221 |    "execution_count": 6,
222 |    "metadata": {
223 |     "collapsed": false,
224 |     "scrolled": true
225 |    },
226 |    "outputs": [
227 |     {
228 |      "data": {
229 |       "text/html": [
230 |        "<div>\n",
231 |        "<style>\n",
232 |        "    .dataframe thead tr:only-child th {\n",
233 |        "        text-align: right;\n",
234 |        "    }\n",
235 |        "\n",
236 |        "    .dataframe thead th {\n",
237 |        "        text-align: left;\n",
238 |        "    }\n",
239 |        "\n",
240 |        "    .dataframe tbody tr th {\n",
241 |        "        vertical-align: top;\n",
242 |        "    }\n",
243 |        "</style>\n",
244 |        "<table border=\"1\" class=\"dataframe\">\n",
245 |        "  <thead>\n",
246 |        "    <tr style=\"text-align: right;\">\n",
247 |        "      <th></th>\n",
248 |        "      <th>nick_name</th>\n",
249 |        "      <th>content</th>\n",
250 |        "      <th>funny_cnt</th>\n",
251 |        "      <th>comment_cnt</th>\n",
252 |        "    </tr>\n",
253 |        "  </thead>\n",
254 |        "  <tbody>\n",
255 |        "    <tr>\n",
256 |        "      <th>0</th>\n",
257 |        "      <td>\\n我家熊孩子不熊\\n</td>\n",
258 |        "      <td>\\n\\n\\n九月份闺蜜来我家吃晚饭。她在用减肥瘦瘦包，这个3600块钱的瘦瘦包要求三个月内晚餐不能吃米饭，不能喝水，不能吃任何荤菜和水果……我说，如果是这样子的话，我不用任何药可以瘦成闪电。闺蜜：不不不，我不行，必须靠药物。三个月过去了，现在的她比原来还胖了10斤，她说是自己没忍住吃了几次晚餐……这货的智商是不是都被脂肪吞噬了！[捂脸][捂脸][捂脸]\\n\\n</td>\n",
259 |        "      <td>758</td>\n",
260 |        "      <td>56</td>\n",
261 |        "    </tr>\n",
262 |        "    <tr>\n",
263 |        "      <th>1</th>\n",
264 |        "      <td>\\n道士下山会女神\\n</td>\n",
265 |        "      <td>\\n\\n\\n银行办点事，小侄跟着去玩，见大堂圣诞树上挂满红包，小孩好奇心重，便挨个去拆开看，结果一无所获，小孩失望的念叨：还大银行，都特么骗人。于是又去摘了个小布娃娃，大堂美女上去阻止，小屁孩居然说：亲我一下我就放回去，来都来了总不能让我空手回去吧！！\\n\\n</td>\n",
266 |        "      <td>807</td>\n",
267 |        "      <td>11</td>\n",
268 |        "    </tr>\n",
269 |        "    <tr>\n",
270 |        "      <th>2</th>\n",
271 |        "      <td>\\n阿丹阿乐\\n</td>\n",
272 |        "      <td>\\n\\n\\n今天我去医院，遇到一位女士，机缘巧合比较聊得来，她说她是来做人工授精的。刚好我是去捐精的，于是我们决定省略中间环节，直接离开医院到她住的地方来了。情况就是这样，我真的没有骗人啊警官！\\n\\n</td>\n",
273 |        "      <td>1457</td>\n",
274 |        "      <td>28</td>\n",
275 |        "    </tr>\n",
276 |        "  </tbody>\n",
277 |        "</table>\n",
278 |        "</div>"
279 |       ],
280 |       "text/plain": [
281 |        "     nick_name                                                                                                                                                                                content  \\\n",
282 |        "0  \\n我家熊孩子不熊\\n  \\n\\n\\n九月份闺蜜来我家吃晚饭。她在用减肥瘦瘦包，这个3600块钱的瘦瘦包要求三个月内晚餐不能吃米饭，不能喝水，不能吃任何荤菜和水果……我说，如果是这样子的话，我不用任何药可以瘦成闪电。闺蜜：不不不，我不行，必须靠药物。三个月过去了，现在的她比原来还胖了10斤，她说是自己没忍住吃了几次晚餐……这货的智商是不是都被脂肪吞噬了！[捂脸][捂脸][捂脸]\\n\\n   \n",
283 |        "1  \\n道士下山会女神\\n                                                     \\n\\n\\n银行办点事，小侄跟着去玩，见大堂圣诞树上挂满红包，小孩好奇心重，便挨个去拆开看，结果一无所获，小孩失望的念叨：还大银行，都特么骗人。于是又去摘了个小布娃娃，大堂美女上去阻止，小屁孩居然说：亲我一下我就放回去，来都来了总不能让我空手回去吧！！\\n\\n   \n",
284 |        "2     \\n阿丹阿乐\\n                                                                                  \\n\\n\\n今天我去医院，遇到一位女士，机缘巧合比较聊得来，她说她是来做人工授精的。刚好我是去捐精的，于是我们决定省略中间环节，直接离开医院到她住的地方来了。情况就是这样，我真的没有骗人啊警官！\\n\\n   \n",
285 |        "\n",
286 |        "  funny_cnt comment_cnt  \n",
287 |        "0       758          56  \n",
288 |        "1       807          11  \n",
289 |        "2      1457          28  "
290 |       ]
291 |      },
292 |      "execution_count": 6,
293 |      "metadata": {},
294 |      "output_type": "execute_result"
295 |     }
296 |    ],
297 |    "source": [
298 |     "df.head(3)"
299 |    ]
300 |   },
301 |   {
302 |    "cell_type": "code",
303 |    "execution_count": null,
304 |    "metadata": {
305 |     "collapsed": true
306 |    },
307 |    "outputs": [],
308 |    "source": [
309 |     "import re\n",
310 |     "import urllib\n",
311 |     "import bs4\n",
312 |     "import pandas as pd\n",
313 |     "from bs4 import BeautifulSoup\n",
314 |     "\n",
315 |     "page = 1 # 第 1 页\n",
316 |     "\n",
317 |     "url = 'http://www.qiushibaike.com/hot/page/' + str(page)\n",
318 |     "header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3236.0 Safari/537.36'}\n",
319 |     "request = urllib.request.Request(url,headers=header)\n",
320 |     "response = urllib.request.urlopen(request).read()\n",
321 |     "\n",
322 |     "content=BeautifulSoup(response, 'lxml')\n",
323 |     "\n",
324 |     "'''\n",
325 |     "1 获取段子内容\n",
326 |     "'''\n",
327 |     "divs = content.find_all('div', class_='content')\n",
328 |     "content_lis=[]\n",
329 |     "for div in divs:\n",
330 |     "    content_lis.append(div.span.get_text())\n",
331 |     "\n",
332 |     "'''\n",
333 |     "2 获取用户昵称\n",
334 |     "''' \n",
335 |     "tmp=content.find_all('div', class_='col1')[0]\n",
336 |     "nick_name_lis=[]\n",
337 |     "for nick_name in tmp.find_all('h2'):\n",
338 |     "    nick_name_lis.append(nick_name.get_text())\n",
339 |     "\n",
340 |     "'''\n",
341 |     "3 获取好笑、评论数量\n",
342 |     "'''\n",
343 |     "counter=0\n",
344 |     "funny_lis=[]\n",
345 |     "comment_lis=[]\n",
346 |     "for cofu in content.find_all('i', class_='number'):\n",
347 |     "    counter+=1\n",
348 |     "    if counter%2!=0:\n",
349 |     "        funny_lis.append(cofu.get_text())\n",
350 |     "    else :\n",
351 |     "        comment_lis.append(cofu.get_text())  \n",
352 |     "\n",
353 |     "'''\n",
354 |     "4 打印当前页\n",
355 |     "'''\n",
356 |     "current_page=content.find_all('ul',class_='pagination')[0].find_all('span',class_='current')[0].get_text()\n",
357 |     "print ('\\033[1;31m[24H] current page:\\033[0m \\033[0;30;43m%s\\033[0m' % (current_page.replace('\\n','')))\n",
358 |     "\n",
359 |     "'''\n",
360 |     "5 转换为 DF并显示\n",
361 |     "'''\n",
362 |     "tdf=pd.DataFrame([nick_name_lis,content_lis,funny_lis,comment_lis])\n",
363 |     "df=tdf.T\n",
364 |     "df.columns=['nick_name','content','funny_cnt','comment_cnt']\n",
365 |     "df.head(3)"
366 |    ]
367 |   }
368 |  ],
369 |  "metadata": {
370 |   "kernelspec": {
371 |    "display_name": "Python 3",
372 |    "language": "python",
373 |    "name": "python3"
374 |   },
375 |   "language_info": {
376 |    "codemirror_mode": {
377 |     "name": "ipython",
378 |     "version": 3
379 |    },
380 |    "file_extension": ".py",
381 |    "mimetype": "text/x-python",
382 |    "name": "python",
383 |    "nbconvert_exporter": "python",
384 |    "pygments_lexer": "ipython3",
385 |    "version": "3.6.3"
386 |   }
387 |  },
388 |  "nbformat": 4,
389 |  "nbformat_minor": 2
390 | }
391 | 


--------------------------------------------------------------------------------
/spider_qiushibaike_content_datas.py:
--------------------------------------------------------------------------------
  1 | 
  2 | # coding: utf-8
  3 | 
  4 | # ### 爬取 糗事百科段子 内容数据
  5 | # ---
  6 | # - author：
  7 | #     - kngines
  8 | # - date：
  9 | #     - 20180118
 10 | 
 11 | # In[1]:
 12 | 
 13 | 
 14 | import re
 15 | import urllib
 16 | import bs4
 17 | import pandas as pd
 18 | from bs4 import BeautifulSoup
 19 | 
 20 | page = 1 # 第 1 页
 21 | 
 22 | url = 'http://www.qiushibaike.com/hot/page/' + str(page)
 23 | header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3236.0 Safari/537.36'}
 24 | request = urllib.request.Request(url,headers=header)
 25 | response = urllib.request.urlopen(request).read()
 26 | 
 27 | content=BeautifulSoup(response, 'lxml')
 28 | 
 29 | '''
 30 | 1 获取段子内容
 31 | '''
 32 | divs = content.find_all('div', class_='content')
 33 | content_lis=[]
 34 | for div in divs:
 35 |     content_lis.append(div.span.get_text())
 36 | 
 37 | '''
 38 | 2 获取用户昵称
 39 | ''' 
 40 | tmp=content.find_all('div', class_='col1')[0]
 41 | nick_name_lis=[]
 42 | for nick_name in tmp.find_all('h2'):
 43 |     nick_name_lis.append(nick_name.get_text())
 44 | 
 45 | '''
 46 | 3 获取好笑、评论数量
 47 | '''
 48 | counter=0
 49 | funny_lis=[]
 50 | comment_lis=[]
 51 | for cofu in content.find_all('i', class_='number'):
 52 |     counter+=1
 53 |     if counter%2!=0:
 54 |         funny_lis.append(cofu.get_text())
 55 |     else :
 56 |         comment_lis.append(cofu.get_text())       
 57 | 
 58 | 
 59 | # ### 1 当前页码信息
 60 | # - 第 1 页
 61 | #     - 通过简单调整，可以实现批量爬取数据
 62 | 
 63 | # In[2]:
 64 | 
 65 | 
 66 | current_page=content.find_all('ul',class_='pagination')[0].find_all('span',class_='current')[0].get_text()
 67 | print ('\033[1;31m[24H] current page:\033[0m \033[0;30;43m%s\033[0m' % (current_page.replace('\n','')))
 68 | 
 69 | 
 70 | # ### 2 转换[DataFrame]并显示
 71 | 
 72 | # In[3]:
 73 | 
 74 | 
 75 | tdf=pd.DataFrame([nick_name_lis,content_lis,funny_lis,comment_lis])
 76 | df=tdf.T
 77 | df.columns=['nick_name','content','funny_cnt','comment_cnt']
 78 | 
 79 | 
 80 | # In[4]:
 81 | 
 82 | 
 83 | df.head(3)
 84 | 
 85 | 
 86 | # ### 3 格式化显示数据
 87 | 
 88 | # In[5]:
 89 | 
 90 | 
 91 | pd.set_option('display.width',200)
 92 | pd.set_option('display.max_columns',20)
 93 | pd.set_option('display.max_rows',50)
 94 | pd.set_option('display.max_colwidth',200)
 95 | 
 96 | 
 97 | # In[6]:
 98 | 
 99 | 
100 | df.head(3)
101 | 
102 | 
103 | # In[ ]:
104 | 
105 | 
106 | import re
107 | import urllib
108 | import bs4
109 | import pandas as pd
110 | from bs4 import BeautifulSoup
111 | 
112 | page = 1 # 第 1 页
113 | 
114 | url = 'http://www.qiushibaike.com/hot/page/' + str(page)
115 | header={'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3236.0 Safari/537.36'}
116 | request = urllib.request.Request(url,headers=header)
117 | response = urllib.request.urlopen(request).read()
118 | 
119 | content=BeautifulSoup(response, 'lxml')
120 | 
121 | '''
122 | 1 获取段子内容
123 | '''
124 | divs = content.find_all('div', class_='content')
125 | content_lis=[]
126 | for div in divs:
127 |     content_lis.append(div.span.get_text())
128 | 
129 | '''
130 | 2 获取用户昵称
131 | ''' 
132 | tmp=content.find_all('div', class_='col1')[0]
133 | nick_name_lis=[]
134 | for nick_name in tmp.find_all('h2'):
135 |     nick_name_lis.append(nick_name.get_text())
136 | 
137 | '''
138 | 3 获取好笑、评论数量
139 | '''
140 | counter=0
141 | funny_lis=[]
142 | comment_lis=[]
143 | for cofu in content.find_all('i', class_='number'):
144 |     counter+=1
145 |     if counter%2!=0:
146 |         funny_lis.append(cofu.get_text())
147 |     else :
148 |         comment_lis.append(cofu.get_text())  
149 | 
150 | '''
151 | 4 打印当前页
152 | '''
153 | current_page=content.find_all('ul',class_='pagination')[0].find_all('span',class_='current')[0].get_text()
154 | print ('\033[1;31m[24H] current page:\033[0m \033[0;30;43m%s\033[0m' % (current_page.replace('\n','')))
155 | 
156 | '''
157 | 5 转换为 DF并显示
158 | '''
159 | tdf=pd.DataFrame([nick_name_lis,content_lis,funny_lis,comment_lis])
160 | df=tdf.T
161 | df.columns=['nick_name','content','funny_cnt','comment_cnt']
162 | df.head(3)
163 | 
164 | 


--------------------------------------------------------------------------------
/users_rise_up_period_data:
--------------------------------------------------------------------------------
 1 | 20170725, 410
 2 | 20170726, 586
 3 | 20170727, 802
 4 | 20170728, 997
 5 | 20170729,1187
 6 | 20170730,1380
 7 | 20170731,1590
 8 | 20170801,1790
 9 | 20170802,1975
10 | 20170803,2135
11 | 20170804,2330
12 | 20170805,2560
13 | 20170806,2742
14 | 20170807,2852
15 | 20170808,3093
16 | 20170809,3331
17 | 20170810,3541
18 | 20170811,3721
19 | 20170812,3901
20 | 20170813,4088
21 | 20170814,4266
22 | 20170815,4477
23 | 20170816,4662
24 | 20170817,4839
25 | 20170818,5042
26 | 20170819,5237
27 | 20170820,5550
28 | 20170821,5736
29 | 20170822,5870
30 | 20170823,5984
31 | 


--------------------------------------------------------------------------------