facilisis

In sagittis

rutrum

condimentum

\nultricies

\n\n\nmaximus\n\n

quis commodo

' 44 | '

one

two

three

split by\nbr
tag

content or set 22 | # by CSS rules) 23 | # apply this function on top of 24 | return WHITESPACE_RE.sub(' ', text) 25 | 26 | 27 | def _squash_artifical_nl(parts): 28 | output, last_nl = [], False 29 | for x in parts: 30 | if x is not None: 31 | output.append(x) 32 | last_nl = False 33 | elif not last_nl: 34 | output.append(None) 35 | last_nl = True 36 | return output 37 | 38 | 39 | def _strip_artifical_nl(parts): 40 | if not parts: 41 | return parts 42 | for start_idx, pt in enumerate(parts): 43 | if isinstance(pt, str): 44 | # 0, 1, 2, index of first string [start_idx:... 45 | break 46 | iterator = enumerate(parts[:start_idx - 1 if start_idx > 0 else None:-1]) 47 | for end_idx, pt in iterator: 48 | if isinstance(pt, str): # 0=None, 1=-1, 2=-2, index of last string 49 | break 50 | return parts[start_idx:-end_idx if end_idx > 0 else None] 51 | 52 | 53 | def _merge_original_parts(parts): 54 | output, orp_buf = [], [] 55 | 56 | def flush(): 57 | if orp_buf: 58 | item = squash_html_whitespace(''.join(orp_buf)).strip() 59 | if item: 60 | output.append(item) 61 | orp_buf[:] = [] 62 | 63 | for x in parts: 64 | if not isinstance(x, str): 65 | flush() 66 | output.append(x) 67 | else: 68 | orp_buf.append(x) 69 | flush() 70 | return output 71 | 72 | 73 | def extract_text_array(dom, squash_artifical_nl=True, strip_artifical_nl=True): 74 | if callable(dom.tag): 75 | return '' 76 | r = [] 77 | if dom.tag in SEPARATORS: 78 | r.append(True) # equivalent of '\n' used to designate separators 79 | elif dom.tag not in INLINE_TAGS: 80 | # equivalent of '\n' used to designate artificially inserted newlines 81 | r.append(None) 82 | if dom.text is not None: 83 | r.append(dom.text) 84 | for child in dom.getchildren(): 85 | r.extend(extract_text_array(child, squash_artifical_nl=False, 86 | strip_artifical_nl=False)) 87 | if child.tail is not None: 88 | r.append(child.tail) 89 | if dom.tag not in INLINE_TAGS and dom.tag not in SEPARATORS: 90 | # equivalent of '\n' used to designate artificially inserted newlines 91 | r.append(None) 92 | if squash_artifical_nl: 93 | r = _squash_artifical_nl(r) 94 | if strip_artifical_nl: 95 | r = _strip_artifical_nl(r) 96 | return r 97 | 98 | 99 | def extract_text(dom, block_symbol='\n', sep_symbol='\n', squash_space=True): 100 | a = extract_text_array(dom, squash_artifical_nl=squash_space) 101 | if squash_space: 102 | a = _strip_artifical_nl(_squash_artifical_nl(_merge_original_parts(a))) 103 | result = ''.join( 104 | block_symbol if x is None else ( 105 | sep_symbol if x is True else x 106 | ) 107 | for x in a 108 | ) 109 | if squash_space: 110 | result = result.strip() 111 | return result 112 | -------------------------------------------------------------------------------- /tests/test_real_browser.py: -------------------------------------------------------------------------------- 1 | import os 2 | import unittest 3 | from threading import Thread 4 | from time import sleep 5 | 6 | from .browser_base import TextExtractionMixin 7 | 8 | SELENIUM = 'MOZ_HEADLESS' in os.environ 9 | 10 | try: 11 | from selenium import webdriver 12 | from selenium.webdriver.firefox.options import Options 13 | except ImportError: 14 | SELENIUM = False 15 | 16 | if SELENIUM: 17 | from urllib.parse import urlunsplit 18 | from http.server import HTTPServer, BaseHTTPRequestHandler 19 | from queue import Queue 20 | 21 | class BaseTestRequestHandler(BaseHTTPRequestHandler): 22 | _last_html = '' 23 | 24 | def _get_last_html(self): 25 | q = self.server.html_queue 26 | while not q.empty(): 27 | self._last_html = q.get_nowait() 28 | return self._last_html 29 | 30 | def log_request(self, code='-', size='-'): 31 | pass 32 | 33 | def recv_from_testsuite(self, non_blocking=False): 34 | q = self.server.in_queue 35 | if non_blocking: 36 | return None if q.empty() else q.get_nowait() 37 | return q.get() 38 | 39 | def send_to_testsuite(self, value): 40 | self.server.out_queue.put(value) 41 | 42 | class HTMLSnippetSender(BaseTestRequestHandler): 43 | last_html = b'' 44 | 45 | def get_last_html(self): 46 | while True: 47 | value = self.recv_from_testsuite(non_blocking=True) 48 | if value is None: 49 | break 50 | self.last_html = value 51 | return self.last_html 52 | 53 | def do_GET(self): 54 | if self.path == '/': 55 | self.send_response(200) 56 | self.send_header('Content-Type', 'text/html; charset=utf-8') 57 | self.end_headers() 58 | self.wfile.write(self.get_last_html().encode('utf-8')) 59 | else: 60 | self.send_response(404) 61 | self.end_headers() 62 | 63 | class BaseBrowserTest(unittest.TestCase): 64 | LOCAL_IP = '127.0.0.1' 65 | PORT = 28546 66 | # descendant of BaseBrowserTestRequestHandler 67 | REQUEST_HANDLER_CLASS = None 68 | 69 | @classmethod 70 | def setUpClass(cls): 71 | cls.to_server_queue = Queue() 72 | cls.from_server_queue = Queue() 73 | cls.server = HTTPServer((cls.LOCAL_IP, cls.PORT), 74 | cls.REQUEST_HANDLER_CLASS) 75 | cls.server.in_queue = cls.to_server_queue 76 | cls.server.out_queue = cls.from_server_queue 77 | cls.server_thread = Thread(target=cls.server.serve_forever) 78 | cls.server_thread.daemon = True 79 | cls.server_thread.start() 80 | options = Options() 81 | options.add_argument('-headless') 82 | cls.driver = webdriver.Firefox(options=options) 83 | sleep(1) 84 | 85 | @classmethod 86 | def tearDownClass(cls): 87 | cls.driver.quit() 88 | cls.server.shutdown() 89 | cls.server.server_close() 90 | 91 | def send_to_server(self, value): 92 | self.to_server_queue.put(value) 93 | 94 | def recv_from_server(self, non_blocking=False): 95 | q = self.from_server_queue 96 | if non_blocking: 97 | return None if q.empty() else q.get_nowait() 98 | return q.get() 99 | 100 | def open_url(self, path): 101 | self.driver.get(urlunsplit( 102 | ('http', '{}:{}'.format( 103 | self.LOCAL_IP, self.PORT), path, '', ''))) 104 | 105 | class TestInnerText(BaseBrowserTest, TextExtractionMixin): 106 | REQUEST_HANDLER_CLASS = HTMLSnippetSender 107 | 108 | def _simple_test(self, html, expected_sq, expected_nosq, **kwargs): 109 | self.send_to_server(html) 110 | self.open_url('/') 111 | 112 | selenium_text = self.driver.find_element_by_tag_name('body').text 113 | self.assertEqual(selenium_text, expected_sq) 114 | 115 | # inner_text = self.driver.execute_script( 116 | # 'return document.body.innerText') 117 | # text_content = self.driver.execute_script( 118 | # 'return document.body.textContent') 119 | -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- 1 | # Makefile for Sphinx documentation 2 | # 3 | 4 | # You can set these variables from the command line. 5 | SPHINXOPTS = 6 | SPHINXBUILD = ../bin/sphinx-build 7 | PAPER = 8 | BUILDDIR = _build 9 | 10 | # Internal variables. 11 | PAPEROPT_a4 = -D latex_paper_size=a4 12 | PAPEROPT_letter = -D latex_paper_size=letter 13 | ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . 14 | # the i18n builder cannot share the environment and doctrees with the others 15 | I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) . 16 | 17 | .PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext 18 | 19 | help: 20 | @echo "Please use \`make ' where is one of" 21 | @echo " html to make standalone HTML files" 22 | @echo " dirhtml to make HTML files named index.html in directories" 23 | @echo " singlehtml to make a single large HTML file" 24 | @echo " pickle to make pickle files" 25 | @echo " json to make JSON files" 26 | @echo " htmlhelp to make HTML files and a HTML help project" 27 | @echo " qthelp to make HTML files and a qthelp project" 28 | @echo " devhelp to make HTML files and a Devhelp project" 29 | @echo " epub to make an epub" 30 | @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter" 31 | @echo " latexpdf to make LaTeX files and run them through pdflatex" 32 | @echo " text to make text files" 33 | @echo " man to make manual pages" 34 | @echo " texinfo to make Texinfo files" 35 | @echo " info to make Texinfo files and run them through makeinfo" 36 | @echo " gettext to make PO message catalogs" 37 | @echo " changes to make an overview of all changed/added/deprecated items" 38 | @echo " linkcheck to check all external links for integrity" 39 | @echo " doctest to run all doctests embedded in the documentation (if enabled)" 40 | 41 | clean: 42 | -rm -rf $(BUILDDIR)/* 43 | 44 | html: 45 | $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html 46 | @echo 47 | @echo "Build finished. The HTML pages are in $(BUILDDIR)/html." 48 | 49 | dirhtml: 50 | $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml 51 | @echo 52 | @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml." 53 | 54 | singlehtml: 55 | $(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml 56 | @echo 57 | @echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml." 58 | 59 | pickle: 60 | $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle 61 | @echo 62 | @echo "Build finished; now you can process the pickle files." 63 | 64 | json: 65 | $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json 66 | @echo 67 | @echo "Build finished; now you can process the JSON files." 68 | 69 | htmlhelp: 70 | $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp 71 | @echo 72 | @echo "Build finished; now you can run HTML Help Workshop with the" \ 73 | ".hhp project file in $(BUILDDIR)/htmlhelp." 74 | 75 | qthelp: 76 | $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp 77 | @echo 78 | @echo "Build finished; now you can run "qcollectiongenerator" with the" \ 79 | ".qhcp project file in $(BUILDDIR)/qthelp, like this:" 80 | @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/chut.qhcp" 81 | @echo "To view the help file:" 82 | @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/chut.qhc" 83 | 84 | devhelp: 85 | $(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp 86 | @echo 87 | @echo "Build finished." 88 | @echo "To view the help file:" 89 | @echo "# mkdir -p $$HOME/.local/share/devhelp/chut" 90 | @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/chut" 91 | @echo "# devhelp" 92 | 93 | epub: 94 | $(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub 95 | @echo 96 | @echo "Build finished. The epub file is in $(BUILDDIR)/epub." 97 | 98 | latex: 99 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex 100 | @echo 101 | @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex." 102 | @echo "Run \`make' in that directory to run these through (pdf)latex" \ 103 | "(use \`make latexpdf' here to do that automatically)." 104 | 105 | latexpdf: 106 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex 107 | @echo "Running LaTeX files through pdflatex..." 108 | $(MAKE) -C $(BUILDDIR)/latex all-pdf 109 | @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." 110 | 111 | text: 112 | $(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text 113 | @echo 114 | @echo "Build finished. The text files are in $(BUILDDIR)/text." 115 | 116 | man: 117 | $(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man 118 | @echo 119 | @echo "Build finished. The manual pages are in $(BUILDDIR)/man." 120 | 121 | texinfo: 122 | $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo 123 | @echo 124 | @echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo." 125 | @echo "Run \`make' in that directory to run these through makeinfo" \ 126 | "(use \`make info' here to do that automatically)." 127 | 128 | info: 129 | $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo 130 | @echo "Running Texinfo files through makeinfo..." 131 | make -C $(BUILDDIR)/texinfo info 132 | @echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo." 133 | 134 | gettext: 135 | $(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale 136 | @echo 137 | @echo "Build finished. The message catalogs are in $(BUILDDIR)/locale." 138 | 139 | changes: 140 | $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes 141 | @echo 142 | @echo "The overview file is in $(BUILDDIR)/changes." 143 | 144 | linkcheck: 145 | $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck 146 | @echo 147 | @echo "Link check complete; look for any errors in the above output " \ 148 | "or in $(BUILDDIR)/linkcheck/output.txt." 149 | 150 | doctest: 151 | $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest 152 | @echo "Testing of doctests in the sources finished, look at the " \ 153 | "results in $(BUILDDIR)/doctest/output.txt." 154 | -------------------------------------------------------------------------------- /CHANGES.rst: -------------------------------------------------------------------------------- 1 | 2.0.2 (unreleased) 2 | ------------------ 3 | 4 | - Nothing changed yet. 5 | 6 | 7 | 2.0.1 (2024-08-30) 8 | ------------------ 9 | 10 | - Breaking change: its seems no longer possible to use the html parser with a xml file so its no longer tested 11 | 12 | - Drop support for python 3.7 13 | 14 | 2.0.0 (2022-12-28) 15 | ------------------ 16 | 17 | - Breaking change: inputs starting with ``"http://"`` or ``"https://"`` like 18 | ``PyQuery("http://example.com")`` will no longer fetch the contents of the URL. 19 | Users desiring the old behavior should switch to ``PyQuery(url="http://example.com")``. 20 | 21 | - Add nextUntil method 22 | 23 | - ``.remove()`` no longer inserts a space in place of the removed element 24 | 25 | - Fix escaping of top-level element text in ``.html()`` output 26 | 27 | - Support (and require) cssselect 1.2+ 28 | 29 | - Drop support for python 3.5/3.6 30 | 31 | 32 | 1.4.3 (2020-11-21) 33 | ------------------ 34 | 35 | - No longer use a universal wheel 36 | 37 | 38 | 1.4.2 (2020-11-21) 39 | ------------------ 40 | 41 | - Fix exception raised when calling `PyQuery("").text()` 42 | 43 | - python2 is no longer supported 44 | 45 | 1.4.1 (2019-10-26) 46 | ------------------ 47 | 48 | - This is the latest release with py2 support 49 | 50 | - Remove py33, py34 support 51 | 52 | - web scraping improvements: default timeout and session support 53 | 54 | - Add API methods to serialize form-related elements according to spec 55 | 56 | - Include HTML markup when querying textarea text/value 57 | 58 | 59 | 1.4.0 (2018-01-11) 60 | ------------------ 61 | 62 | - Refactoring of `.text()` to match firefox behavior. 63 | 64 | 65 | 1.3.0 (2017-10-21) 66 | ------------------ 67 | 68 | - Remove some unmaintained modules: ``pyquery.ajax`` and ``pyquery.rules`` 69 | 70 | - Code cleanup. No longer use ugly hacks required by python2.6/python3.2. 71 | 72 | - Run tests with python3.6 on CI 73 | 74 | - Add a ``method`` argument to ``.outer_html()`` 75 | 76 | 77 | 1.2.17 (2016-10-14) 78 | ------------------- 79 | 80 | - ``PyQuery('').val()`` is ``''`` 81 | - ``PyQuery('').val()`` is ``''`` 82 | 83 | 84 | 1.2.16 (2016-10-14) 85 | ------------------- 86 | 87 | - ``.attr('value', '')`` no longer removes the ``value`` attribute 88 | 89 | - ```` without ``value="..."`` have a ``.val()`` of 90 | ``'on'`` 91 | 92 | - ```` without ``value="..."`` have a ``.val()`` of 93 | ``'on'`` 94 | 95 | - ``

and <select>, to match jQuery behavior
113 | 
114 | 
115 | 1.2.13 (2016-04-12)
116 | -------------------
117 | 
118 | - Note explicit support for Python 3.5
119 | 
120 | 1.2.12 (2016-04-12)
121 | -------------------
122 | 
123 | - make_links_absolute now take care of whitespaces
124 | 
125 | - added pseudo selector :has()
126 | 
127 | - add cookies arguments as allowed arguments for requests
128 | 
129 | 
130 | 1.2.11 (2016-02-02)
131 | -------------------
132 | 
133 | - Preserve namespaces attribute on PyQuery copies.
134 | 
135 | - Do not raise an error when the http response code is 2XX
136 | 
137 | 1.2.10 (2016-01-05)
138 | -------------------
139 | 
140 | - Fixed #118: implemented usage ``lxml.etree.tostring`` within ``outer_html`` method
141 | 
142 | - Fixed #117: Raise HTTP Error if HTTP status code is not equal to 200
143 | 
144 | - Fixed #112: make_links_absolute does not apply to form actions
145 | 
146 | - Fixed #98: contains act like jQuery
147 | 
148 | 
149 | 1.2.9 (2014-08-22)
150 | ------------------
151 | 
152 | - Support for keyword arguments in PyQuery custom functions
153 | 
154 | - Fixed #78: items must take care or the parent
155 | 
156 | - Fixed #65 PyQuery.make_links_absolute() no longer creates 'href' attribute
157 |   when it isn't there
158 | 
159 | - Fixed #19. ``is_()`` was broken.
160 | 
161 | - Fixed #9. ``.replaceWith(PyQuery element)`` raises error
162 | 
163 | - Remove official python3.2 support (mostly because of 3rd party semi-deps)
164 | 
165 | 
166 | 1.2.8 (2013-12-21)
167 | ------------------
168 | 
169 | - Fixed #22: Open by filename fails when file contains invalid xml
170 | 
171 | - Bug fix in .remove_class()
172 | 
173 | 
174 | 1.2.7 (2013-12-21)
175 | ------------------
176 | 
177 | - Use pep8 name for methods but keep an alias for camel case method.
178 |   Eg: remove_attr and removeAttr works
179 |   Fix #57
180 | 
181 | - .text() now return an empty string instead of None if there is no text node.
182 |   Fix #45
183 | 
184 | - Fixed #23: removeClass adds class attribute to elements which previously
185 |   lacked one
186 | 
187 | 
188 | 1.2.6 (2013-10-11)
189 | ------------------
190 | 
191 | - README_fixt.py was not include in the release. Fix #54.
192 | 
193 | 
194 | 1.2.5 (2013-10-10)
195 | ------------------
196 | 
197 | - cssselect compat. See https://github.com/SimonSapin/cssselect/pull/22
198 | 
199 | - tests improvements. no longer require a eth connection.
200 | 
201 | - fix #55
202 | 
203 | 1.2.4
204 | -----
205 | 
206 | - Moved to github. So a few files are renamed from .txt to .rst
207 | 
208 | - Added .xhtml_to_html() and .remove_namespaces()
209 | 
210 | - Use requests to fetch urls (if available)
211 | 
212 | - Use restkit's proxy instead of Paste (which will die with py3)
213 | 
214 | - Allow to open https urls
215 | 
216 | - python2.5 is no longer supported (may work, but tests are broken)
217 | 
218 | 1.2.3
219 | -----
220 | 
221 | - Allow to pass this in .filter() callback
222 | 
223 | - Add .contents() .items()
224 | 
225 | - Add tox.ini
226 | 
227 | - Bug fixes: fix #35 #55 #64 #66
228 | 
229 | 1.2.2
230 | -----
231 | 
232 | - Fix cssselectpatch to match the newer implementation of cssselect. Fixes issue #62, #52 and #59 (Haoyu Bai)
233 | 
234 | - Fix issue #37 (Caleb Burns)
235 | 
236 | 1.2.1
237 | -----
238 | 
239 | - Allow to use a custom css translator.
240 | 
241 | - Fix issue 44: case problem with xml documents
242 | 
243 | 1.2
244 | ---
245 | 
246 | - PyQuery now uses `cssselect <http://pypi.python.org/pypi/cssselect>`_. See issue 43.
247 | 
248 | - Fix issue 40: forward .html() extra arguments to ``lxml.etree.tostring``
249 | 
250 | 1.1.1
251 | -----
252 | 
253 | - Minor release. Include test file so you can run tests from the tarball.
254 | 
255 | 
256 | 1.1
257 | ---
258 | 
259 | - fix issues 30, 31, 32 - py3 improvements / webob 1.2+ support
260 | 
261 | 
262 | 1.0
263 | ---
264 | 
265 | - fix issues 24
266 | 
267 | 0.7
268 | ---
269 | 
270 | - Python 3 compatible
271 | 
272 | - Add __unicode__ method
273 | 
274 | - Add root and encoding attribute
275 | 
276 | - fix issues 19, 20, 22, 23
277 | 
278 | 0.6.1
279 | ------
280 | 
281 | - Move README.txt at package root
282 | 
283 | - Add CHANGES.txt and add it to long_description
284 | 
285 | 0.6
286 | ----
287 | 
288 | - Added PyQuery.outerHtml
289 | 
290 | - Added PyQuery.fn
291 | 
292 | - Added PyQuery.map
293 | 
294 | - Change PyQuery.each behavior to reflect jQuery api
295 | 
296 | 
297 |

--------------------------------------------------------------------------------
/docs/pseudo_classes.rst:
--------------------------------------------------------------------------------
  1 | =========================
  2 | Using pseudo classes
  3 | =========================
  4 | 
  5 | 
  6 | :button
  7 | ==================
  8 | 
  9 | Matches all button input elements and the button element::
 10 | 
 11 |         >>> from pyquery import PyQuery
 12 |         >>> d = PyQuery(('<div><input type="button"/>'
 13 |         ...          '<button></button></div>'))
 14 |         >>> d(':button')
 15 |         [<input>, <button>]
 16 | 
 17 |     
 18 | 
 19 | :checkbox
 20 | ==================
 21 | 
 22 | Matches all checkbox input elements::
 23 | 
 24 |         >>> from pyquery import PyQuery
 25 |         >>> d = PyQuery('<div><input type="checkbox"/></div>')
 26 |         >>> d('input:checkbox')
 27 |         [<input>]
 28 | 
 29 |     
 30 | 
 31 | :checked
 32 | ==================
 33 | 
 34 | Matches odd elements, zero-indexed::
 35 | 
 36 |         >>> from pyquery import PyQuery
 37 |         >>> d = PyQuery('<div><input checked="checked"/></div>')
 38 |         >>> d('input:checked')
 39 |         [<input>]
 40 | 
 41 |     
 42 | 
 43 | :child
 44 | ==================
 45 | 
 46 | right is an immediate child of left
 47 | 
 48 | :contains()
 49 | ==================
 50 | 
 51 | Matches all elements that contain the given text
 52 | 
 53 |         >>> from pyquery import PyQuery
 54 |         >>> d = PyQuery('<div><h1/><h1 class="title">title</h1></div>')
 55 |         >>> d('h1:contains("title")')
 56 |         [<h1.title>]
 57 | 
 58 |     
 59 | 
 60 | :descendant
 61 | ==================
 62 | 
 63 | right is a child, grand-child or further descendant of left
 64 | 
 65 | :disabled
 66 | ==================
 67 | 
 68 | Matches all elements that are disabled::
 69 | 
 70 |         >>> from pyquery import PyQuery
 71 |         >>> d = PyQuery('<div><input disabled="disabled"/></div>')
 72 |         >>> d('input:disabled')
 73 |         [<input>]
 74 | 
 75 |     
 76 | 
 77 | :empty
 78 | ==================
 79 | 
 80 | Match all elements that do not contain other elements::
 81 | 
 82 |         >>> from pyquery import PyQuery
 83 |         >>> d = PyQuery('<div><h1><span>title</span></h1><h2/></div>')
 84 |         >>> d(':empty')
 85 |         [<h2>]
 86 | 
 87 |     
 88 | 
 89 | :enabled
 90 | ==================
 91 | 
 92 | Matches all elements that are enabled::
 93 | 
 94 |         >>> from pyquery import PyQuery
 95 |         >>> d = PyQuery('<div><input value="foo" /></div>')
 96 |         >>> d('input:enabled')
 97 |         [<input>]
 98 | 
 99 |     
100 | 
101 | :eq()
102 | ==================
103 | 
104 | Matches a single element by its index::
105 | 
106 |         >>> from pyquery import PyQuery
107 |         >>> d = PyQuery('<div><h1 class="first"/><h1 class="last"/></div>')
108 |         >>> d('h1:eq(0)')
109 |         [<h1.first>]
110 |         >>> d('h1:eq(1)')
111 |         [<h1.last>]
112 | 
113 |     
114 | 
115 | :even
116 | ==================
117 | 
118 | Matches even elements, zero-indexed::
119 | 
120 |         >>> from pyquery import PyQuery
121 |         >>> d = PyQuery('<div><p></p><p class="last"></p></div>')
122 |         >>> d('p:even')
123 |         [<p>]
124 | 
125 |     
126 | 
127 | :file
128 | ==================
129 | 
130 | Matches all input elements of type file::
131 | 
132 |         >>> from pyquery import PyQuery
133 |         >>> d = PyQuery('<div><input type="file"/></div>')
134 |         >>> d('input:file')
135 |         [<input>]
136 | 
137 |     
138 | 
139 | :first
140 | ==================
141 | 
142 | Matches the first selected element::
143 | 
144 |         >>> from pyquery import PyQuery
145 |         >>> d = PyQuery('<div><p class="first"></p><p></p></div>')
146 |         >>> d('p:first')
147 |         [<p.first>]
148 | 
149 |     
150 | 
151 | :gt()
152 | ==================
153 | 
154 | Matches all elements with an index over the given one::
155 | 
156 |         >>> from pyquery import PyQuery
157 |         >>> d = PyQuery('<div><h1 class="first"/><h1 class="last"/></div>')
158 |         >>> d('h1:gt(0)')
159 |         [<h1.last>]
160 | 
161 |     
162 | 
163 | :has()
164 | ==================
165 | 
166 | Matches elements which contain at least one element that matches
167 |     the specified selector. https://api.jquery.com/has-selector/
168 | 
169 |         >>> from pyquery import PyQuery
170 |         >>> d = PyQuery('<div class="foo"><div class="bar"></div></div>')
171 |         >>> d('.foo:has(".baz")')
172 |         []
173 |         >>> d('.foo:has(".foo")')
174 |         []
175 |         >>> d('.foo:has(".bar")')
176 |         [<div.foo>]
177 |         >>> d('.foo:has(div)')
178 |         [<div.foo>]
179 | 
180 |     
181 | 
182 | :header
183 | ==================
184 | 
185 | Matches all header elements (h1, ..., h6)::
186 | 
187 |         >>> from pyquery import PyQuery
188 |         >>> d = PyQuery('<div><h1>title</h1></div>')
189 |         >>> d(':header')
190 |         [<h1>]
191 | 
192 |     
193 | 
194 | :hidden
195 | ==================
196 | 
197 | Matches all hidden input elements::
198 | 
199 |         >>> from pyquery import PyQuery
200 |         >>> d = PyQuery('<div><input type="hidden"/></div>')
201 |         >>> d('input:hidden')
202 |         [<input>]
203 | 
204 |     
205 | 
206 | :image
207 | ==================
208 | 
209 | Matches all image input elements::
210 | 
211 |         >>> from pyquery import PyQuery
212 |         >>> d = PyQuery('<div><input type="image"/></div>')
213 |         >>> d('input:image')
214 |         [<input>]
215 | 
216 |     
217 | 
218 | :input
219 | ==================
220 | 
221 | Matches all input elements::
222 | 
223 |         >>> from pyquery import PyQuery
224 |         >>> d = PyQuery(('<div><input type="file"/>'
225 |         ...          '<textarea>

')) 226 | >>> d(':input') 227 | [,

]
228 | 
229 |     
230 | 
231 | :last
232 | ==================
233 | 
234 | Matches the last selected element::
235 | 
236 |         >>> from pyquery import PyQuery
237 |         >>> d = PyQuery('<div><p></p><p class="last"></p></div>')
238 |         >>> d('p:last')
239 |         [<p.last>]
240 | 
241 |     
242 | 
243 | :lt()
244 | ==================
245 | 
246 | Matches all elements with an index below the given one::
247 | 
248 |         >>> from pyquery import PyQuery
249 |         >>> d = PyQuery('<div><h1 class="first"/><h1 class="last"/></div>')
250 |         >>> d('h1:lt(1)')
251 |         [<h1.first>]
252 | 
253 |     
254 | 
255 | :odd
256 | ==================
257 | 
258 | Matches odd elements, zero-indexed::
259 | 
260 |         >>> from pyquery import PyQuery
261 |         >>> d = PyQuery('<div><p></p><p class="last"></p></div>')
262 |         >>> d('p:odd')
263 |         [<p.last>]
264 | 
265 |     
266 | 
267 | :parent
268 | ==================
269 | 
270 | Match all elements that contain other elements::
271 | 
272 |         >>> from pyquery import PyQuery
273 |         >>> d = PyQuery('<div><h1><span>title</span></h1><h1/></div>')
274 |         >>> d('h1:parent')
275 |         [<h1>]
276 | 
277 |     
278 | 
279 | :password
280 | ==================
281 | 
282 | Matches all password input elements::
283 | 
284 |         >>> from pyquery import PyQuery
285 |         >>> d = PyQuery('<div><input type="password"/></div>')
286 |         >>> d('input:password')
287 |         [<input>]
288 | 
289 |     
290 | 
291 | :pseudo
292 | ==================
293 | 
294 | Translate a pseudo-element.
295 | 
296 |     Defaults to not supporting pseudo-elements at all,
297 |     but can be overridden by sub-classes
298 | 
299 | :radio
300 | ==================
301 | 
302 | Matches all radio input elements::
303 | 
304 |         >>> from pyquery import PyQuery
305 |         >>> d = PyQuery('<div><input type="radio"/></div>')
306 |         >>> d('input:radio')
307 |         [<input>]
308 | 
309 |     
310 | 
311 | :reset
312 | ==================
313 | 
314 | Matches all reset input elements::
315 | 
316 |         >>> from pyquery import PyQuery
317 |         >>> d = PyQuery('<div><input type="reset"/></div>')
318 |         >>> d('input:reset')
319 |         [<input>]
320 | 
321 |     
322 | 
323 | :selected
324 | ==================
325 | 
326 | Matches all elements that are selected::
327 | 
328 |         >>> from pyquery import PyQuery
329 |         >>> d = PyQuery('<select><option selected="selected"/></select>')
330 |         >>> d('option:selected')
331 |         [<option>]
332 | 
333 |     
334 | 
335 | :submit
336 | ==================
337 | 
338 | Matches all submit input elements::
339 | 
340 |         >>> from pyquery import PyQuery
341 |         >>> d = PyQuery('<div><input type="submit"/></div>')
342 |         >>> d('input:submit')
343 |         [<input>]
344 | 
345 |     
346 | 
347 | :text
348 | ==================
349 | 
350 | Matches all text input elements::
351 | 
352 |         >>> from pyquery import PyQuery
353 |         >>> d = PyQuery('<div><input type="text"/></div>')
354 |         >>> d('input:text')
355 |         [<input>]
356 | 
357 |

--------------------------------------------------------------------------------
/docs/conf.py:
--------------------------------------------------------------------------------
  1 | #
  2 | # pyquery documentation build configuration file, created by
  3 | # sphinx-quickstart on Thu Nov  1 21:48:09 2012.
  4 | #
  5 | # This file is execfile()d with the current directory set to its containing dir.
  6 | #
  7 | # Note that not all possible configuration values are present in this
  8 | # autogenerated file.
  9 | #
 10 | # All configuration values have a default; values that are commented out
 11 | # serve to show the default.
 12 | 
 13 | # If extensions (or modules to document with autodoc) are in another directory,
 14 | # add these directories to sys.path here. If the directory is relative to the
 15 | # documentation root, use os.path.abspath to make it absolute, like shown here.
 16 | # sys.path.insert(0, os.path.abspath('.'))
 17 | 
 18 | from os import path
 19 | 
 20 | # -- General configuration -----------------------------------------------------
 21 | 
 22 | # If your documentation needs a minimal Sphinx version, state it here.
 23 | # needs_sphinx = '1.0'
 24 | 
 25 | # Add any Sphinx extension module names here, as strings. They can be extensions
 26 | # coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
 27 | extensions = ['sphinx.ext.autodoc', 'sphinx.ext.viewcode']
 28 | 
 29 | # Add any paths that contain templates here, relative to this directory.
 30 | templates_path = ['_templates']
 31 | 
 32 | # The suffix of source filenames.
 33 | source_suffix = '.rst'
 34 | 
 35 | # The encoding of source files.
 36 | # source_encoding = 'utf-8-sig'
 37 | 
 38 | # The master toctree document.
 39 | master_doc = 'index'
 40 | 
 41 | # General information about the project.
 42 | project = 'pyquery'
 43 | copyright = '2012-2017, Olivier Lauzanne'
 44 | 
 45 | # The version info for the project you're documenting, acts as replacement for
 46 | # |version| and |release|, also used in various other places throughout the
 47 | # built documents.
 48 | #
 49 | # The short X.Y version.
 50 | version = '2.0.x'
 51 | # The full version, including alpha/beta/rc tags.
 52 | release = '2.0.x'
 53 | 
 54 | # The language for content autogenerated by Sphinx. Refer to documentation
 55 | # for a list of supported languages.
 56 | # language = None
 57 | 
 58 | # There are two options for replacing |today|: either, you set today to some
 59 | # non-false value, then it is used:
 60 | # today = ''
 61 | # Else, today_fmt is used as the format for a strftime call.
 62 | # today_fmt = '%B %d, %Y'
 63 | 
 64 | # List of patterns, relative to source directory, that match files and
 65 | # directories to ignore when looking for source files.
 66 | exclude_patterns = ['_build']
 67 | 
 68 | # The reST default role (used for this markup: `text`) to use for all documents.
 69 | # default_role = None
 70 | 
 71 | # If true, '()' will be appended to :func: etc. cross-reference text.
 72 | # add_function_parentheses = True
 73 | 
 74 | # If true, the current module name will be prepended to all description
 75 | # unit titles (such as .. function::).
 76 | # add_module_names = True
 77 | 
 78 | # If true, sectionauthor and moduleauthor directives will be shown in the
 79 | # output. They are ignored by default.
 80 | # show_authors = False
 81 | 
 82 | # The name of the Pygments (syntax highlighting) style to use.
 83 | pygments_style = 'sphinx'
 84 | 
 85 | # A list of ignored prefixes for module index sorting.
 86 | # modindex_common_prefix = []
 87 | 
 88 | 
 89 | # -- Options for HTML output ---------------------------------------------------
 90 | 
 91 | # The theme to use for HTML and HTML Help pages.  See the documentation for
 92 | # a list of builtin themes.
 93 | html_theme = 'nature'
 94 | 
 95 | # Theme options are theme-specific and customize the look and feel of a theme
 96 | # further.  For a list of options available for each theme, see the
 97 | # documentation.
 98 | # html_theme_options = {}
 99 | 
100 | # Add any paths that contain custom themes here, relative to this directory.
101 | # html_theme_path = []
102 | 
103 | # The name for this set of Sphinx documents.  If None, it defaults to
104 | # "<project> v<release> documentation".
105 | # html_title = None
106 | 
107 | # A shorter title for the navigation bar.  Default is the same as html_title.
108 | # html_short_title = None
109 | 
110 | # The name of an image file (relative to this directory) to place at the top
111 | # of the sidebar.
112 | # html_logo = None
113 | 
114 | # The name of an image file (within the static path) to use as favicon of the
115 | # docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
116 | # pixels large.
117 | # html_favicon = None
118 | 
119 | # Add any paths that contain custom static files (such as style sheets) here,
120 | # relative to this directory. They are copied after the builtin static files,
121 | # so a file named "default.css" will overwrite the builtin "default.css".
122 | html_static_path = ['_static']
123 | 
124 | # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
125 | # using the given strftime format.
126 | # html_last_updated_fmt = '%b %d, %Y'
127 | 
128 | # If true, SmartyPants will be used to convert quotes and dashes to
129 | # typographically correct entities.
130 | # html_use_smartypants = True
131 | 
132 | # Custom sidebar templates, maps document names to template names.
133 | # html_sidebars = {}
134 | 
135 | # Additional templates that should be rendered to pages, maps page names to
136 | # template names.
137 | # html_additional_pages = {}
138 | 
139 | # If false, no module index is generated.
140 | # html_domain_indices = True
141 | 
142 | # If false, no index is generated.
143 | # html_use_index = True
144 | 
145 | # If true, the index is split into individual pages for each letter.
146 | # html_split_index = False
147 | 
148 | # If true, links to the reST sources are added to the pages.
149 | # html_show_sourcelink = True
150 | 
151 | # If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
152 | # html_show_sphinx = True
153 | 
154 | # If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
155 | # html_show_copyright = True
156 | 
157 | # If true, an OpenSearch description file will be output, and all pages will
158 | # contain a <link> tag referring to it.  The value of this option must be the
159 | # base URL from which the finished HTML is served.
160 | # html_use_opensearch = ''
161 | 
162 | # This is the file name suffix for HTML files (e.g. ".xhtml").
163 | # html_file_suffix = None
164 | 
165 | # Output file base name for HTML help builder.
166 | htmlhelp_basename = 'pyquerydoc'
167 | 
168 | 
169 | # -- Options for LaTeX output --------------------------------------------------
170 | 
171 | latex_elements = {
172 |     # The paper size ('letterpaper' or 'a4paper').
173 |     # 'papersize': 'letterpaper',
174 |     # The font size ('10pt', '11pt' or '12pt').
175 |     # 'pointsize': '10pt',
176 |     # Additional stuff for the LaTeX preamble.
177 |     # 'preamble': '',
178 | }
179 | 
180 | # Grouping the document tree into LaTeX files. List of tuples
181 | # (source start file, target name, title, author, documentclass [howto/manual]).
182 | latex_documents = [
183 |     (
184 |         'index',
185 |         'pyquery.tex',
186 |         'pyquery Documentation',
187 |         'Olivier Lauzanne',
188 |         'manual',
189 |     ),
190 | ]
191 | 
192 | # The name of an image file (relative to this directory) to place at the top of
193 | # the title page.
194 | # latex_logo = None
195 | 
196 | # For "manual" documents, if this is true, then toplevel headings are parts,
197 | # not chapters.
198 | # latex_use_parts = False
199 | 
200 | # If true, show page references after internal links.
201 | # latex_show_pagerefs = False
202 | 
203 | # If true, show URL addresses after external links.
204 | # latex_show_urls = False
205 | 
206 | # Documents to append as an appendix to all manuals.
207 | # latex_appendices = []
208 | 
209 | # If false, no module index is generated.
210 | # latex_domain_indices = True
211 | 
212 | 
213 | # -- Options for manual page output --------------------------------------------
214 | 
215 | # One entry per manual page. List of tuples
216 | # (source start file, name, description, authors, manual section).
217 | man_pages = [
218 |     ('index', 'pyquery', 'pyquery Documentation', ['Olivier Lauzanne'], 1)
219 | ]
220 | 
221 | # If true, show URL addresses after external links.
222 | # man_show_urls = False
223 | 
224 | 
225 | # -- Options for Texinfo output ------------------------------------------------
226 | 
227 | # Grouping the document tree into Texinfo files. List of tuples
228 | # (source start file, target name, title, author,
229 | #  dir menu entry, description, category)
230 | texinfo_documents = [
231 |     (
232 |         'index',
233 |         'pyquery',
234 |         'pyquery Documentation',
235 |         'Olivier Lauzanne',
236 |         'pyquery',
237 |         'One line description of project.',
238 |         'Miscellaneous',
239 |     ),
240 | ]
241 | 
242 | # Documents to append as an appendix to all manuals.
243 | # texinfo_appendices = []
244 | 
245 | # If false, no module index is generated.
246 | # texinfo_domain_indices = True
247 | 
248 | # How to display URL addresses: 'footnote', 'no', or 'inline'.
249 | # texinfo_show_urls = 'footnote'
250 | 
251 | 
252 | pkg_dir = path.abspath(__file__).split('/docs')[0]
253 | setup = path.join(pkg_dir, 'setup.py')
254 | if path.isfile(setup):
255 |     for line_ in open(setup):
256 |         if line_.startswith("version"):
257 |             version = line_.split('=')[-1]
258 |             version = version.strip()
259 |             version = version.strip("'\"")
260 |             release = version
261 |             break
262 | del pkg_dir, setup, path
263 | 
264 | try:
265 |     from pyquery.cssselectpatch import JQueryTranslator
266 | except ImportError:
267 |     pass
268 | else:
269 |     with open('pseudo_classes.rst', 'w') as fd:
270 |         fd.write('=========================\n')
271 |         fd.write('Using pseudo classes\n')
272 |         fd.write('=========================\n')
273 |         for k in sorted(dir(JQueryTranslator)):
274 |             if k.startswith('xpath_'):
275 |                 attr = getattr(JQueryTranslator, k)
276 |                 doc = getattr(attr, '__doc__', '') or ''
277 |                 doc = doc.strip()
278 |                 if doc.startswith('Common implementation'):
279 |                     continue
280 |                 k = k[6:]
281 |                 if '_' not in k or not doc:
282 |                     continue
283 |                 k, t = k.split('_', 1)
284 |                 if '_' in t:
285 |                     continue
286 |                 if t == 'function':
287 |                     k += '()'
288 |                 fd.write('\n\n:%s\n' % k)
289 |                 fd.write('==================\n\n')
290 |                 fd.write(doc.strip('..').replace('        ', '    '))
291 |

')) 196 | >>> d(':input') 197 | [,

434 | 437 | ''' 438 | 439 | html4 = ''' 440 | 444 | 449 | 451 | 456 | ''' 457 | 458 | html6 = ''' 459 | 464 | 469 | 474 | ''' 475 | 476 | html5 = ''' 477 |

478 | 479 | 480 | 481 |

482 | ''' 483 | 484 | def test_attr_empty_string(self): 485 | d = pq('

') 486 | d.attr('value', '') 487 | self.assertEqual(d.outer_html(), '

') 488 | self.assertEqual(d.outer_html(method="xml"), '

Not MeReplace MeNot Me

' + inner_html + '

' 630 | d = pq(html) 631 | self.assertEqual(d.html(), inner_html) 632 | 633 | 634 | class TestAjax(TestCase): 635 | 636 | html = ''' 637 |

638 | 639 |

640 | 646 | 649 | 653 | ''' 654 | 655 | html2 = ''' 656 | 663 | 668 | ''' 669 | 670 | html3 = ''' 671 | 687 | ''' 688 | 689 | html4 = ''' 690 | 703 | ''' 704 | 705 | def test_serialize_pairs_form_id(self): 706 | d = pq(self.html) 707 | self.assertEqual(d('#div').serialize_pairs(), []) 708 | self.assertEqual(d('#dispersed').serialize_pairs(), [ 709 | ('order', 'spam'), ('order', 'eggs'), ('order', 'ham'), 710 | ('order', 'tomato'), ('order', 'baked beans'), 711 | ]) 712 | self.assertEqual(d('.no-id').serialize_pairs(), [ 713 | ('spam', 'Spam'), 714 | ]) 715 | 716 | def test_serialize_pairs_form_controls(self): 717 | d = pq(self.html2) 718 | self.assertEqual(d('fieldset').serialize_pairs(), [ 719 | ('fieldset', 'eggs'), ('fieldset', 'ham'), 720 | ]) 721 | self.assertEqual(d('#input, fieldset, #first').serialize_pairs(), [ 722 | ('order', 'spam'), ('fieldset', 'eggs'), ('fieldset', 'ham'), 723 | ('fieldset', 'eggs'), ('fieldset', 'ham'), ('fieldset', 'ham'), 724 | ]) 725 | self.assertEqual(d('#datalist').serialize_pairs(), [ 726 | ('datalist', 'eggs'), ('checkbox', 'on'), ('radio', 'on'), 727 | ]) 728 | 729 | def test_serialize_pairs_filter_controls(self): 730 | d = pq(self.html3) 731 | self.assertEqual(d('form').serialize_pairs(), [ 732 | ('order', 'spam') 733 | ]) 734 | 735 | def test_serialize_pairs_form_values(self): 736 | d = pq(self.html4) 737 | self.assertEqual(d('form').serialize_pairs(), [ 738 | ('spam', 'Spam/spam'), ('order', 'baked\r\nbeans'), 739 | ('order', 'tomato'), ('multiline', 'multiple\r\nlines\r\nof text'), 740 | ]) 741 | 742 | def test_serialize_array(self): 743 | d = pq(self.html4) 744 | self.assertEqual(d('form').serialize_array(), [ 745 | {'name': 'spam', 'value': 'Spam/spam'}, 746 | {'name': 'order', 'value': 'baked\r\nbeans'}, 747 | {'name': 'order', 'value': 'tomato'}, 748 | {'name': 'multiline', 'value': 'multiple\r\nlines\r\nof text'}, 749 | ]) 750 | 751 | def test_serialize(self): 752 | d = pq(self.html4) 753 | self.assertEqual( 754 | d('form').serialize(), 755 | 'spam=Spam%2Fspam&order=baked%0D%0Abeans&order=tomato&' 756 | 'multiline=multiple%0D%0Alines%0D%0Aof%20text' 757 | ) 758 | 759 | def test_serialize_dict(self): 760 | d = pq(self.html4) 761 | self.assertEqual(d('form').serialize_dict(), { 762 | 'spam': 'Spam/spam', 763 | 'order': ['baked\r\nbeans', 'tomato'], 764 | 'multiline': 'multiple\r\nlines\r\nof text', 765 | }) 766 | 767 | 768 | class TestMakeLinks(TestCase): 769 | 770 | html = ''' 771 | 772 |

773 | with href 774 | without href 775 |

776 | 777 | ''' 778 | 779 | def test_make_link(self): 780 | d = pq(self.html, parser='xml') 781 | d.make_links_absolute(base_url='http://example.com') 782 | self.assertTrue(len(d('a[href]')), 1) 783 | self.assertEqual(d('a[href]').attr('href'), 784 | 'http://example.com/path_info') 785 | 786 | 787 | class TestHTMLParser(TestCase): 788 | xml = "

I'm valid XML

" 789 | html = '''

790 | TestimageMy link text 791 | imageMy link text 2 792 | Behind you, a three-headed HTML‐Entity! 793 |

803 | TestimageMy link text 804 | imageMy link text 2 805 | Behind you, a three-headed HTML&dash;Entity! 806 |

814 | TestimageMy link text 815 | imageMy link text 2 816 | Behind you, a three-headed HTML&dash;Entity! 817 |

''' 818 | d = pq(self.html) 819 | d('a').replace_with(lambda i, e: pq(e).html()) 820 | val = d.__html__() 821 | assert val == expected, (repr(val), repr(expected)) 822 | 823 | 824 | class TestXMLNamespace(TestCase): 825 | xml = ''' 826 | 827 | What 828 | 123 829 | 830 | 831 | 832 | ''' 833 | 834 | xhtml = ''' 835 | 836 | 837 |

What

838 | 839 | ''' 840 | 841 | namespaces = {'bar': 'http://example.com/bar', 842 | 'baz': 'http://example.com/baz'} 843 | 844 | def test_selector(self): 845 | expected = 'What' 846 | d = pq(self.xml.encode('utf8'), parser='xml') 847 | val = d('bar|blah', 848 | namespaces=self.namespaces).text() 849 | self.assertEqual(repr(val), repr(expected)) 850 | 851 | def test_selector_with_xml(self): 852 | expected = 'What' 853 | d = pq('bar|blah', self.xml.encode('utf8'), parser='xml', 854 | namespaces=self.namespaces) 855 | val = d.text() 856 | self.assertEqual(repr(val), repr(expected)) 857 | 858 | def test_xhtml_namespace(self): 859 | expected = 'What' 860 | d = pq(self.xhtml.encode('utf8'), parser='xml') 861 | d.xhtml_to_html() 862 | val = d('div').text() 863 | self.assertEqual(repr(val), repr(expected)) 864 | 865 | def test_xhtml_namespace_html_parser(self): 866 | expected = 'What' 867 | d = pq(self.xhtml, parser='html') 868 | d.xhtml_to_html() 869 | val = d('div').text() 870 | self.assertEqual(repr(val), repr(expected)) 871 | 872 | def test_remove_namespaces(self): 873 | expected = 'What' 874 | d = pq(self.xml.encode('utf8'), parser='xml').remove_namespaces() 875 | val = d('blah').text() 876 | self.assertEqual(repr(val), repr(expected)) 877 | 878 | def test_persistent_namespaces(self): 879 | d = pq(self.xml.encode('utf8'), parser='xml', 880 | namespaces=self.namespaces) 881 | val = d('bar|blah').text() 882 | self.assertEqual(repr(val), repr('What')) 883 | 884 | def test_namespace_traversal(self): 885 | d = pq(self.xml.encode('utf8'), parser='xml', 886 | namespaces=self.namespaces) 887 | val = d('baz|subbaz').closest('baz|baz').attr('a') 888 | self.assertEqual(repr(val), repr('b')) 889 | 890 | 891 | class TestWebScrapping(TestCase): 892 | 893 | def setUp(self): 894 | self.s = http.StopableWSGIServer.create(debug_app) 895 | self.s.wait() 896 | self.application_url = self.s.application_url.rstrip('/') 897 | 898 | def test_get(self): 899 | d = pq(url=self.application_url, data={'q': 'foo'}, 900 | method='get') 901 | print(d) 902 | self.assertIn('REQUEST_METHOD: GET', d('p').text()) 903 | self.assertIn('q=foo', d('p').text()) 904 | 905 | def test_post(self): 906 | d = pq(url=self.application_url, data={'q': 'foo'}, 907 | method='post') 908 | self.assertIn('REQUEST_METHOD: POST', d('p').text()) 909 | self.assertIn('q=foo', d('p').text()) 910 | 911 | def test_session(self): 912 | if HAS_REQUEST: 913 | import requests 914 | session = requests.Session() 915 | session.headers.update({'X-FOO': 'bar'}) 916 | d = pq(url=self.application_url, data={'q': 'foo'}, 917 | method='get', session=session) 918 | self.assertIn('HTTP_X_FOO: bar', d('p').text()) 919 | else: 920 | self.skipTest('no requests library') 921 | 922 | def tearDown(self): 923 | self.s.shutdown() 924 | 925 | 926 | class TestWebScrappingEncoding(TestCase): 927 | 928 | def test_get(self): 929 | d = pq(url='http://ru.wikipedia.org/wiki/Заглавная_страница', 930 | method='get') 931 | print(d) 932 | self.assertEqual(d('#pt-login').text(), 'Войти') 933 | 934 | 935 | class TestWebScrappingTimeouts(TestCase): 936 | 937 | def setUp(self): 938 | def app(environ, start_response): 939 | start_response('200 OK', [('Content-Type', 'text/plain')]) 940 | time.sleep(2) 941 | return [b'foobar\n'] 942 | self.s = http.StopableWSGIServer.create(app) 943 | self.s.wait() 944 | self.application_url = self.s.application_url.rstrip('/') 945 | 946 | def test_get(self): 947 | pq(url=self.application_url) 948 | with self.assertRaises(Exception): 949 | pq(url=self.application_url, timeout=1) 950 | 951 | def tearDown(self): 952 | self.s.shutdown() 953 | -------------------------------------------------------------------------------- /pyquery/pyquery.py: -------------------------------------------------------------------------------- 1 | # Copyright (C) 2008 - Olivier Lauzanne 2 | # 3 | # Distributed under the BSD license, see LICENSE.txt 4 | from .cssselectpatch import JQueryTranslator 5 | from reprlib import recursive_repr 6 | from urllib.parse import urlencode 7 | from urllib.parse import urljoin 8 | from .openers import url_opener 9 | from .text import extract_text 10 | from copy import deepcopy 11 | from html import escape 12 | from lxml import etree 13 | import lxml.html 14 | import inspect 15 | import itertools 16 | import types 17 | import sys 18 | 19 | if sys.version_info >= (3, 12, 0): 20 | from collections import OrderedDict 21 | else: 22 | # backward compat. to be able to run doctest with 3.7+. see: 23 | # https://github.com/gawel/pyquery/issues/249 24 | # and: 25 | # https://github.com/python/cpython/blob/3.12/Lib/collections/__init__.py#L272 26 | from collections import OrderedDict as BaseOrderedDict 27 | 28 | class OrderedDict(BaseOrderedDict): 29 | @recursive_repr() 30 | def __repr__(self): 31 | 'od.__repr__() <==> repr(od)' 32 | if not self: 33 | return '%s()' % (self.__class__.__name__,) 34 | return '%s(%r)' % (self.__class__.__name__, dict(self.items())) 35 | 36 | basestring = (str, bytes) 37 | 38 | 39 | def getargspec(func): 40 | args = inspect.signature(func).parameters.values() 41 | return [p.name for p in args 42 | if p.kind == p.POSITIONAL_OR_KEYWORD] 43 | 44 | 45 | def with_camel_case_alias(func): 46 | """decorator for methods who required a camelcase alias""" 47 | _camel_case_aliases.add(func.__name__) 48 | return func 49 | 50 | 51 | _camel_case_aliases = set() 52 | 53 | 54 | def build_camel_case_aliases(PyQuery): 55 | """add camelcase aliases to PyQuery""" 56 | for alias in _camel_case_aliases: 57 | parts = list(alias.split('_')) 58 | name = parts[0] + ''.join([p.title() for p in parts[1:]]) 59 | func = getattr(PyQuery, alias) 60 | f = types.FunctionType(func.__code__, func.__globals__, 61 | name, func.__defaults__) 62 | f.__doc__ = ( 63 | 'Alias for :func:`~pyquery.pyquery.PyQuery.%s`') % func.__name__ 64 | setattr(PyQuery, name, f.__get__(None, PyQuery)) 65 | 66 | 67 | def fromstring(context, parser=None, custom_parser=None): 68 | """use html parser if we don't have clean xml 69 | """ 70 | if hasattr(context, 'read') and hasattr(context.read, '__call__'): 71 | meth = 'parse' 72 | else: 73 | meth = 'fromstring' 74 | if custom_parser is None: 75 | if parser is None: 76 | try: 77 | result = getattr(etree, meth)(context) 78 | except etree.XMLSyntaxError: 79 | if hasattr(context, 'seek'): 80 | context.seek(0) 81 | result = getattr(lxml.html, meth)(context) 82 | if isinstance(result, etree._ElementTree): 83 | return [result.getroot()] 84 | else: 85 | return [result] 86 | elif parser == 'xml': 87 | custom_parser = getattr(etree, meth) 88 | elif parser == 'html': 89 | custom_parser = getattr(lxml.html, meth) 90 | elif parser == 'html5': 91 | from lxml.html import html5parser 92 | custom_parser = getattr(html5parser, meth) 93 | elif parser == 'soup': 94 | from lxml.html import soupparser 95 | custom_parser = getattr(soupparser, meth) 96 | elif parser == 'html_fragments': 97 | custom_parser = lxml.html.fragments_fromstring 98 | else: 99 | raise ValueError('No such parser: "%s"' % parser) 100 | 101 | result = custom_parser(context) 102 | if isinstance(result, list): 103 | return result 104 | elif isinstance(result, etree._ElementTree): 105 | return [result.getroot()] 106 | elif result is not None: 107 | return [result] 108 | else: 109 | return [] 110 | 111 | 112 | def callback(func, *args): 113 | return func(*args[:func.__code__.co_argcount]) 114 | 115 | 116 | class NoDefault(object): 117 | def __repr__(self): 118 | """clean representation in Sphinx""" 119 | return '' 120 | 121 | 122 | no_default = NoDefault() 123 | del NoDefault 124 | 125 | 126 | class FlexibleElement(object): 127 | """property to allow a flexible api""" 128 | def __init__(self, pget, pset=no_default, pdel=no_default): 129 | self.pget = pget 130 | self.pset = pset 131 | self.pdel = pdel 132 | 133 | def __get__(self, instance, klass): 134 | class _element(object): 135 | """real element to support set/get/del attr and item and js call 136 | style""" 137 | def __call__(prop, *args, **kwargs): 138 | return self.pget(instance, *args, **kwargs) 139 | __getattr__ = __getitem__ = __setattr__ = __setitem__ = __call__ 140 | 141 | def __delitem__(prop, name): 142 | if self.pdel is not no_default: 143 | return self.pdel(instance, name) 144 | else: 145 | raise NotImplementedError() 146 | __delattr__ = __delitem__ 147 | 148 | def __repr__(prop): 149 | return '' % self.pget.__name__ 150 | return _element() 151 | 152 | def __set__(self, instance, value): 153 | if self.pset is not no_default: 154 | self.pset(instance, value) 155 | else: 156 | raise NotImplementedError() 157 | 158 | 159 | class PyQuery(list): 160 | """The main class 161 | """ 162 | 163 | _translator_class = JQueryTranslator 164 | 165 | def __init__(self, *args, **kwargs): 166 | html = None 167 | elements = [] 168 | self._base_url = None 169 | self.parser = kwargs.pop('parser', None) 170 | 171 | if 'parent' in kwargs: 172 | self._parent = kwargs.pop('parent') 173 | else: 174 | self._parent = no_default 175 | 176 | if 'css_translator' in kwargs: 177 | self._translator = kwargs.pop('css_translator') 178 | elif self.parser in ('xml',): 179 | self._translator = self._translator_class(xhtml=True) 180 | elif self._parent is not no_default: 181 | self._translator = self._parent._translator 182 | else: 183 | self._translator = self._translator_class(xhtml=False) 184 | 185 | self.namespaces = kwargs.pop('namespaces', None) 186 | 187 | if kwargs: 188 | # specific case to get the dom 189 | if 'filename' in kwargs: 190 | html = open(kwargs['filename'], 191 | encoding=kwargs.get('encoding')) 192 | elif 'url' in kwargs: 193 | url = kwargs.pop('url') 194 | if 'opener' in kwargs: 195 | opener = kwargs.pop('opener') 196 | html = opener(url, **kwargs) 197 | else: 198 | html = url_opener(url, kwargs) 199 | if not self.parser: 200 | self.parser = 'html' 201 | self._base_url = url 202 | else: 203 | raise ValueError('Invalid keyword arguments %s' % kwargs) 204 | 205 | elements = fromstring(html, self.parser) 206 | # close open descriptor if possible 207 | if hasattr(html, 'close'): 208 | try: 209 | html.close() 210 | except Exception: 211 | pass 212 | 213 | else: 214 | # get nodes 215 | 216 | # determine context and selector if any 217 | selector = context = no_default 218 | length = len(args) 219 | if length == 1: 220 | context = args[0] 221 | elif length == 2: 222 | selector, context = args 223 | else: 224 | raise ValueError( 225 | "You can't do that. Please, provide arguments") 226 | 227 | # get context 228 | if isinstance(context, basestring): 229 | try: 230 | elements = fromstring(context, self.parser) 231 | except Exception: 232 | raise 233 | elif isinstance(context, self.__class__): 234 | # copy 235 | elements = context[:] 236 | elif isinstance(context, list): 237 | elements = context 238 | elif isinstance(context, etree._Element): 239 | elements = [context] 240 | else: 241 | raise TypeError(context) 242 | 243 | # select nodes 244 | if elements and selector is not no_default: 245 | xpath = self._css_to_xpath(selector) 246 | results = [] 247 | for tag in elements: 248 | results.extend( 249 | tag.xpath(xpath, namespaces=self.namespaces)) 250 | elements = results 251 | 252 | list.__init__(self, elements) 253 | 254 | def _css_to_xpath(self, selector, prefix='descendant-or-self::'): 255 | selector = selector.replace('[@', '[') 256 | return self._translator.css_to_xpath(selector, prefix) 257 | 258 | def _copy(self, *args, **kwargs): 259 | kwargs.setdefault('namespaces', self.namespaces) 260 | return self.__class__(*args, **kwargs) 261 | 262 | def __call__(self, *args, **kwargs): 263 | """return a new PyQuery instance 264 | """ 265 | length = len(args) 266 | if length == 0: 267 | raise ValueError('You must provide at least a selector') 268 | if args[0] == '': 269 | return self._copy([]) 270 | if (len(args) == 1 and 271 | isinstance(args[0], str) and 272 | not args[0].startswith('<')): 273 | args += (self,) 274 | result = self._copy(*args, parent=self, **kwargs) 275 | return result 276 | 277 | # keep original list api prefixed with _ 278 | _append = list.append 279 | _extend = list.extend 280 | 281 | # improve pythonic api 282 | def __add__(self, other): 283 | assert isinstance(other, self.__class__) 284 | return self._copy(self[:] + other[:]) 285 | 286 | def extend(self, other): 287 | """Extend with another PyQuery object""" 288 | assert isinstance(other, self.__class__) 289 | self._extend(other[:]) 290 | return self 291 | 292 | def items(self, selector=None): 293 | """Iter over elements. Return PyQuery objects: 294 | 295 | >>> d = PyQuery('

foobar

') 296 | >>> [i.text() for i in d.items('span')] 297 | ['foo', 'bar'] 298 | >>> [i.text() for i in d('span').items()] 299 | ['foo', 'bar'] 300 | >>> list(d.items('a')) == list(d('a').items()) 301 | True 302 | """ 303 | if selector: 304 | elems = self(selector) or [] 305 | else: 306 | elems = self 307 | for elem in elems: 308 | yield self._copy(elem, parent=self) 309 | 310 | def xhtml_to_html(self): 311 | """Remove xhtml namespace: 312 | 313 | >>> doc = PyQuery( 314 | ... '') 315 | >>> doc 316 | [<{http://www.w3.org/1999/xhtml}html>] 317 | >>> doc.xhtml_to_html() 318 | [] 319 | """ 320 | try: 321 | root = self[0].getroottree() 322 | except IndexError: 323 | pass 324 | else: 325 | lxml.html.xhtml_to_html(root) 326 | return self 327 | 328 | def remove_namespaces(self): 329 | """Remove all namespaces: 330 | 331 | >>> doc = PyQuery('') 332 | >>> doc 333 | [<{http://example.com/foo}foo>] 334 | >>> doc.remove_namespaces() 335 | [] 336 | """ 337 | try: 338 | root = self[0].getroottree() 339 | except IndexError: 340 | pass 341 | else: 342 | for el in root.iter('{*}*'): 343 | if el.tag.startswith('{'): 344 | el.tag = el.tag.split('}', 1)[1] 345 | return self 346 | 347 | def __str__(self): 348 | """xml representation of current nodes:: 349 | 350 | >>> xml = PyQuery( 351 | ... '', parser='html_fragments') 352 | >>> print(str(xml)) 353 | 354 | 355 | """ 356 | return ''.join([etree.tostring(e, encoding=str) for e in self]) 357 | 358 | def __unicode__(self): 359 | """xml representation of current nodes""" 360 | return u''.join([etree.tostring(e, encoding=str) 361 | for e in self]) 362 | 363 | def __html__(self): 364 | """html representation of current nodes:: 365 | 366 | >>> html = PyQuery( 367 | ... '', parser='html_fragments') 368 | >>> print(html.__html__()) 369 | 370 | 371 | """ 372 | return u''.join([lxml.html.tostring(e, encoding=str) 373 | for e in self]) 374 | 375 | def __repr__(self): 376 | r = [] 377 | try: 378 | for el in self: 379 | c = el.get('class') 380 | c = c and '.' + '.'.join(c.split(' ')) or '' 381 | id = el.get('id') 382 | id = id and '#' + id or '' 383 | r.append('<%s%s%s>' % (el.tag, id, c)) 384 | return '[' + (', '.join(r)) + ']' 385 | except AttributeError: 386 | return list.__repr__(self) 387 | 388 | @property 389 | def root(self): 390 | """return the xml root element 391 | """ 392 | if self._parent is not no_default: 393 | return self._parent[0].getroottree() 394 | return self[0].getroottree() 395 | 396 | @property 397 | def encoding(self): 398 | """return the xml encoding of the root element 399 | """ 400 | root = self.root 401 | if root is not None: 402 | return self.root.docinfo.encoding 403 | 404 | ############## 405 | # Traversing # 406 | ############## 407 | 408 | def _filter_only(self, selector, elements, reverse=False, unique=False): 409 | """Filters the selection set only, as opposed to also including 410 | descendants. 411 | """ 412 | if selector is None: 413 | results = elements 414 | else: 415 | xpath = self._css_to_xpath(selector, 'self::') 416 | results = [] 417 | for tag in elements: 418 | results.extend(tag.xpath(xpath, namespaces=self.namespaces)) 419 | if reverse: 420 | results.reverse() 421 | if unique: 422 | result_list = results 423 | results = [] 424 | for item in result_list: 425 | if item not in results: 426 | results.append(item) 427 | return self._copy(results, parent=self) 428 | 429 | def parent(self, selector=None): 430 | return self._filter_only( 431 | selector, 432 | [e.getparent() for e in self if e.getparent() is not None], 433 | unique=True) 434 | 435 | def prev(self, selector=None): 436 | return self._filter_only( 437 | selector, 438 | [e.getprevious() for e in self if e.getprevious() is not None]) 439 | 440 | def next(self, selector=None): 441 | return self._filter_only( 442 | selector, 443 | [e.getnext() for e in self if e.getnext() is not None]) 444 | 445 | def _traverse(self, method): 446 | for e in self: 447 | current = getattr(e, method)() 448 | while current is not None: 449 | yield current 450 | current = getattr(current, method)() 451 | 452 | def _traverse_parent_topdown(self): 453 | for e in self: 454 | this_list = [] 455 | current = e.getparent() 456 | while current is not None: 457 | this_list.append(current) 458 | current = current.getparent() 459 | this_list.reverse() 460 | for j in this_list: 461 | yield j 462 | 463 | def _next_all(self): 464 | return [e for e in self._traverse('getnext')] 465 | 466 | @with_camel_case_alias 467 | def next_all(self, selector=None): 468 | """ 469 | >>> h = '

Bye

' 470 | >>> d = PyQuery(h) 471 | >>> d('p:last').next_all() 472 | [] 473 | >>> d('p:last').nextAll() 474 | [] 475 | """ 476 | return self._filter_only(selector, self._next_all()) 477 | 478 | @with_camel_case_alias 479 | def next_until(self, selector, filter_=None): 480 | """ 481 | >>> h = ''' 482 | ...

Greeting 1

483 | ...

Hello!

World!

484 | ...

Greeting 2

Bye!

485 | ... ''' 486 | >>> d = PyQuery(h) 487 | >>> d('h2:first').nextUntil('h2') 488 | [

] 489 | """ 490 | return self._filter_only( 491 | filter_, [ 492 | e 493 | for q in itertools.takewhile( 494 | lambda q: not q.is_(selector), self.next_all().items()) 495 | for e in q 496 | ] 497 | ) 498 | 499 | def _prev_all(self): 500 | return [e for e in self._traverse('getprevious')] 501 | 502 | @with_camel_case_alias 503 | def prev_all(self, selector=None): 504 | """ 505 | >>> h = '

Bye

' 506 | >>> d = PyQuery(h) 507 | >>> d('p:last').prev_all() 508 | [] 509 | >>> d('p:last').prevAll() 510 | [] 511 | """ 512 | return self._filter_only(selector, self._prev_all(), reverse=True) 513 | 514 | def siblings(self, selector=None): 515 | """ 516 | >>> h = '

Bye

' 517 | >>> d = PyQuery(h) 518 | >>> d('.hello').siblings() 519 | [

, ] 520 | >>> d('.hello').siblings('img') 521 | [] 522 | 523 | """ 524 | return self._filter_only(selector, self._prev_all() + self._next_all()) 525 | 526 | def parents(self, selector=None): 527 | """ 528 | >>> d = PyQuery('

Bye

') 529 | >>> d('p').parents() 530 | [] 531 | >>> d('.hello').parents('span') 532 | [] 533 | >>> d('.hello').parents('p') 534 | [] 535 | """ 536 | return self._filter_only( 537 | selector, 538 | [e for e in self._traverse_parent_topdown()], 539 | unique=True 540 | ) 541 | 542 | def children(self, selector=None): 543 | """Filter elements that are direct children of self using optional 544 | selector: 545 | 546 | >>> d = PyQuery('

Bye

') 547 | >>> d 548 | [] 549 | >>> d.children() 550 | [,

] 551 | >>> d.children('.hello') 552 | [] 553 | """ 554 | elements = [child for tag in self for child in tag.getchildren()] 555 | return self._filter_only(selector, elements) 556 | 557 | def closest(self, selector=None): 558 | """ 559 | >>> d = PyQuery( 560 | ... '

This is a ' 561 | ... 'test

Bye

') 596 | >>> d('p') 597 | [,

] 598 | >>> d('p').filter('.hello') 599 | [] 600 | >>> d('p').filter(lambda i: i == 1) 601 | [

Bye

') 628 | >>> d('p').not_('.hello') 629 | [

Bye

') 640 | >>> d('p').eq(0).is_('.hello') 641 | True 642 | 643 | >>> d('p').eq(0).is_('span') 644 | False 645 | 646 | >>> d('p').eq(1).is_('.hello') 647 | False 648 | 649 | .. 650 | """ 651 | return bool(self._filter_only(selector, self)) 652 | 653 | def find(self, selector): 654 | """Find elements using selector traversing down from self: 655 | 656 | >>> m = '

Whoah!

there

' 657 | >>> d = PyQuery(m) 658 | >>> d('p').find('em') 659 | [, ] 660 | >>> d('p').eq(1).find('em') 661 | [] 662 | """ 663 | xpath = self._css_to_xpath(selector) 664 | results = [child.xpath(xpath, namespaces=self.namespaces) 665 | for tag in self 666 | for child in tag.getchildren()] 667 | # Flatten the results 668 | elements = [] 669 | for r in results: 670 | elements.extend(r) 671 | return self._copy(elements, parent=self) 672 | 673 | def eq(self, index): 674 | """Return PyQuery of only the element with the provided index:: 675 | 676 | >>> d = PyQuery('
Hi
Bye
') 677 | >>> d('p').eq(0) 678 | [] 679 | >>> d('p').eq(1) 680 | [
] 681 | >>> d('p').eq(2) 682 | [] 683 | 684 | .. 685 | """ 686 | # Slicing will return empty list when index=-1 687 | # we should handle out of bound by ourselves 688 | try: 689 | items = self[index] 690 | except IndexError: 691 | items = [] 692 | return self._copy(items, parent=self) 693 | 694 | def each(self, func): 695 | """apply func on each nodes 696 | """ 697 | try: 698 | for i, element in enumerate(self): 699 | func.__globals__['this'] = element 700 | if callback(func, i, element) is False: 701 | break 702 | finally: 703 | f_globals = func.__globals__ 704 | if 'this' in f_globals: 705 | del f_globals['this'] 706 | return self 707 | 708 | def map(self, func): 709 | """Returns a new PyQuery after transforming current items with func. 710 | 711 | func should take two arguments - 'index' and 'element'. Elements can 712 | also be referred to as 'this' inside of func:: 713 | 714 | >>> d = PyQuery('
Hi there
Bye

') 715 | >>> d('p').map(lambda i, e: PyQuery(e).text()) 716 | ['Hi there', 'Bye'] 717 | 718 | >>> d('p').map(lambda i, e: len(PyQuery(this).text())) 719 | [8, 3] 720 | 721 | >>> d('p').map(lambda i, e: PyQuery(this).text().split()) 722 | ['Hi', 'there', 'Bye'] 723 | 724 | """ 725 | items = [] 726 | try: 727 | for i, element in enumerate(self): 728 | func.__globals__['this'] = element 729 | result = callback(func, i, element) 730 | if result is not None: 731 | if not isinstance(result, list): 732 | items.append(result) 733 | else: 734 | items.extend(result) 735 | finally: 736 | f_globals = func.__globals__ 737 | if 'this' in f_globals: 738 | del f_globals['this'] 739 | return self._copy(items, parent=self) 740 | 741 | @property 742 | def length(self): 743 | return len(self) 744 | 745 | def size(self): 746 | return len(self) 747 | 748 | def end(self): 749 | """Break out of a level of traversal and return to the parent level. 750 | 751 | >>> m = '
Whoah!
there
' 752 | >>> d = PyQuery(m) 753 | >>> d('p').eq(1).find('em').end().end() 754 | [
,
] 755 | """ 756 | return self._parent 757 | 758 | ############## 759 | # Attributes # 760 | ############## 761 | def attr(self, *args, **kwargs): 762 | """Attributes manipulation 763 | """ 764 | 765 | mapping = {'class_': 'class', 'for_': 'for'} 766 | 767 | attr = value = no_default 768 | length = len(args) 769 | if length == 1: 770 | attr = args[0] 771 | attr = mapping.get(attr, attr) 772 | elif length == 2: 773 | attr, value = args 774 | attr = mapping.get(attr, attr) 775 | elif kwargs: 776 | attr = {} 777 | for k, v in kwargs.items(): 778 | attr[mapping.get(k, k)] = v 779 | else: 780 | raise ValueError('Invalid arguments %s %s' % (args, kwargs)) 781 | 782 | if not self: 783 | return None 784 | elif isinstance(attr, dict): 785 | for tag in self: 786 | for key, value in attr.items(): 787 | tag.set(key, value) 788 | elif value is no_default: 789 | return self[0].get(attr) 790 | elif value is None: 791 | return self.remove_attr(attr) 792 | else: 793 | for tag in self: 794 | tag.set(attr, value) 795 | return self 796 | 797 | @with_camel_case_alias 798 | def remove_attr(self, name): 799 | """Remove an attribute:: 800 | 801 | >>> d = PyQuery('
') 802 | >>> d.remove_attr('id') 803 | [
] 804 | >>> d.removeAttr('id') 805 | [
] 806 | 807 | .. 808 | """ 809 | for tag in self: 810 | try: 811 | del tag.attrib[name] 812 | except KeyError: 813 | pass 814 | return self 815 | 816 | attr = FlexibleElement(pget=attr, pdel=remove_attr) 817 | 818 | ####### 819 | # CSS # 820 | ####### 821 | def height(self, value=no_default): 822 | """set/get height of element 823 | """ 824 | return self.attr('height', value) 825 | 826 | def width(self, value=no_default): 827 | """set/get width of element 828 | """ 829 | return self.attr('width', value) 830 | 831 | @with_camel_case_alias 832 | def has_class(self, name): 833 | """Return True if element has class:: 834 | 835 | >>> d = PyQuery('
') 836 | >>> d.has_class('myclass') 837 | True 838 | >>> d.hasClass('myclass') 839 | True 840 | 841 | .. 842 | """ 843 | return self.is_('.%s' % name) 844 | 845 | @with_camel_case_alias 846 | def add_class(self, value): 847 | """Add a css class to elements:: 848 | 849 | >>> d = PyQuery('
') 850 | >>> d.add_class('myclass') 851 | [] 852 | >>> d.addClass('myclass') 853 | [] 854 | 855 | .. 856 | """ 857 | for tag in self: 858 | values = value.split(' ') 859 | classes = (tag.get('class') or '').split() 860 | classes += [v for v in values if v not in classes] 861 | tag.set('class', ' '.join(classes)) 862 | return self 863 | 864 | @with_camel_case_alias 865 | def remove_class(self, value): 866 | """Remove a css class to elements:: 867 | 868 | >>> d = PyQuery('
') 869 | >>> d.remove_class('myclass') 870 | [
] 871 | >>> d.removeClass('myclass') 872 | [
] 873 | 874 | .. 875 | """ 876 | for tag in self: 877 | values = value.split(' ') 878 | classes = set((tag.get('class') or '').split()) 879 | classes.difference_update(values) 880 | classes.difference_update(['']) 881 | classes = ' '.join(classes) 882 | if classes.strip(): 883 | tag.set('class', classes) 884 | elif tag.get('class'): 885 | tag.set('class', classes) 886 | return self 887 | 888 | @with_camel_case_alias 889 | def toggle_class(self, value): 890 | """Toggle a css class to elements 891 | 892 | >>> d = PyQuery('
') 893 | >>> d.toggle_class('myclass') 894 | [] 895 | >>> d.toggleClass('myclass') 896 | [
] 897 | 898 | """ 899 | for tag in self: 900 | values = value.split(' ') 901 | classes = (tag.get('class') or '').split() 902 | values_to_add = [v for v in values if v not in classes] 903 | values_to_del = [v for v in values if v in classes] 904 | classes = [v for v in classes if v not in values_to_del] 905 | classes += values_to_add 906 | tag.set('class', ' '.join(classes)) 907 | return self 908 | 909 | def css(self, *args, **kwargs): 910 | """css attributes manipulation 911 | """ 912 | 913 | attr = value = no_default 914 | length = len(args) 915 | if length == 1: 916 | attr = args[0] 917 | elif length == 2: 918 | attr, value = args 919 | elif kwargs: 920 | attr = kwargs 921 | else: 922 | raise ValueError('Invalid arguments %s %s' % (args, kwargs)) 923 | 924 | if isinstance(attr, dict): 925 | for tag in self: 926 | stripped_keys = [key.strip().replace('_', '-') 927 | for key in attr.keys()] 928 | current = [el.strip() 929 | for el in (tag.get('style') or '').split(';') 930 | if el.strip() 931 | and el.split(':')[0].strip() not in stripped_keys] 932 | for key, value in attr.items(): 933 | key = key.replace('_', '-') 934 | current.append('%s: %s' % (key, value)) 935 | tag.set('style', '; '.join(current)) 936 | elif isinstance(value, basestring): 937 | attr = attr.replace('_', '-') 938 | for tag in self: 939 | current = [ 940 | el.strip() 941 | for el in (tag.get('style') or '').split(';') 942 | if (el.strip() and 943 | not el.split(':')[0].strip() == attr.strip())] 944 | current.append('%s: %s' % (attr, value)) 945 | tag.set('style', '; '.join(current)) 946 | return self 947 | 948 | css = FlexibleElement(pget=css, pset=css) 949 | 950 | ################### 951 | # CORE UI EFFECTS # 952 | ################### 953 | def hide(self): 954 | """Add display:none to elements style: 955 | 956 | >>> print(PyQuery('
').hide()) 957 |
958 | 959 | """ 960 | return self.css('display', 'none') 961 | 962 | def show(self): 963 | """Add display:block to elements style: 964 | 965 | >>> print(PyQuery('
').show()) 966 |
967 | 968 | """ 969 | return self.css('display', 'block') 970 | 971 | ######## 972 | # HTML # 973 | ######## 974 | def val(self, value=no_default): 975 | """Set the attribute value:: 976 | 977 | >>> d = PyQuery('') 978 | >>> d.val('Youhou') 979 | [] 980 | 981 | Get the attribute value:: 982 | 983 | >>> d.val() 984 | 'Youhou' 985 | 986 | Set the selected values for a `select` element with the `multiple` 987 | attribute:: 988 | 989 | >>> d = PyQuery(''' 990 | ... 993 | ... ''') 994 | >>> d.val(['you', 'hou']) 995 | [1006 | if tag.tag == 'textarea': 1007 | return self._copy(tag).html() 1008 | # <select> 1009 | elif tag.tag == 'select': 1010 | if 'multiple' in tag.attrib: 1011 | # Only extract value if selected 1012 | selected = self._copy(tag)('option[selected]') 1013 | # Rebuild list to avoid serialization error 1014 | return list(selected.map( 1015 | lambda _, o: self._copy(o).attr('value') 1016 | )) 1017 | selected_option = self._copy(tag)('option[selected]:last') 1018 | if selected_option: 1019 | return selected_option.attr('value') 1020 | else: 1021 | return self._copy(tag)('option').attr('value') 1022 | # <input type="checkbox"> or <input type="radio"> 1023 | elif self.is_(':checkbox,:radio'): 1024 | val = self._copy(tag).attr('value') 1025 | if val is None: 1026 | return 'on' 1027 | else: 1028 | return val 1029 | # <input> 1030 | elif tag.tag == 'input': 1031 | val = self._copy(tag).attr('value') 1032 | return val.replace('\n', '') if val else '' 1033 | # everything else. 1034 | return self._copy(tag).attr('value') or '' 1035 | 1036 | def _set_value(pq, value): 1037 | for tag in pq: 1038 | # <select> 1039 | if tag.tag == 'select': 1040 | if not isinstance(value, list): 1041 | value = [value] 1042 | 1043 | def _make_option_selected(_, elem): 1044 | pq = self._copy(elem) 1045 | if pq.attr('value') in value: 1046 | pq.attr('selected', 'selected') 1047 | if 'multiple' not in tag.attrib: 1048 | del value[:] # Ensure it toggles first match 1049 | else: 1050 | pq.removeAttr('selected') 1051 | 1052 | self._copy(tag)('option').each(_make_option_selected) 1053 | continue 1054 | # Stringify array 1055 | if isinstance(value, list): 1056 | value = ','.join(value) 1057 | # <textarea> 1058 | if tag.tag == 'textarea': 1059 | self._copy(tag).text(value) 1060 | continue 1061 | # <input> and everything else. 1062 | self._copy(tag).attr('value', value) 1063 | 1064 | if value is no_default: 1065 | if len(self): 1066 | return _get_value(self[0]) 1067 | else: 1068 | _set_value(self, value) 1069 | return self 1070 | 1071 | def html(self, value=no_default, **kwargs): 1072 | """Get or set the html representation of sub nodes. 1073 | 1074 | Get the text value:: 1075 | 1076 | >>> d = PyQuery('<div><span>toto</span></div>') 1077 | >>> print(d.html()) 1078 | <span>toto</span> 1079 | 1080 | Extra args are passed to ``lxml.etree.tostring``:: 1081 | 1082 | >>> d = PyQuery('<div><span></span></div>') 1083 | >>> print(d.html()) 1084 | <span/> 1085 | >>> print(d.html(method='html')) 1086 | <span></span> 1087 | 1088 | Set the text value:: 1089 | 1090 | >>> d.html('<span>Youhou !</span>') 1091 | [<div>] 1092 | >>> print(d) 1093 | <div><span>Youhou !</span></div> 1094 | """ 1095 | if value is no_default: 1096 | if not self: 1097 | return None 1098 | tag = self[0] 1099 | children = tag.getchildren() 1100 | html = escape(tag.text or '', quote=False) 1101 | if not children: 1102 | return html 1103 | if 'encoding' not in kwargs: 1104 | kwargs['encoding'] = str 1105 | html += u''.join([etree.tostring(e, **kwargs) 1106 | for e in children]) 1107 | return html 1108 | else: 1109 | if isinstance(value, self.__class__): 1110 | new_html = str(value) 1111 | elif isinstance(value, basestring): 1112 | new_html = value 1113 | elif not value: 1114 | new_html = '' 1115 | else: 1116 | raise ValueError(type(value)) 1117 | 1118 | for tag in self: 1119 | for child in tag.getchildren(): 1120 | tag.remove(child) 1121 | root = fromstring( 1122 | u'<root>' + new_html + u'</root>', 1123 | self.parser)[0] 1124 | children = root.getchildren() 1125 | if children: 1126 | tag.extend(children) 1127 | tag.text = root.text 1128 | return self 1129 | 1130 | @with_camel_case_alias 1131 | def outer_html(self, method="html"): 1132 | """Get the html representation of the first selected element:: 1133 | 1134 | >>> d = PyQuery('<div><span class="red">toto</span> rocks</div>') 1135 | >>> print(d('span')) 1136 | <span class="red">toto</span> rocks 1137 | >>> print(d('span').outer_html()) 1138 | <span class="red">toto</span> 1139 | >>> print(d('span').outerHtml()) 1140 | <span class="red">toto</span> 1141 | 1142 | >>> S = PyQuery('<p>Only <b>me</b> & myself</p>') 1143 | >>> print(S('b').outer_html()) 1144 | <b>me</b> 1145 | 1146 | .. 1147 | """ 1148 | 1149 | if not self: 1150 | return None 1151 | e0 = self[0] 1152 | if e0.tail: 1153 | e0 = deepcopy(e0) 1154 | e0.tail = '' 1155 | return etree.tostring(e0, encoding=str, method=method) 1156 | 1157 | def text(self, value=no_default, **kwargs): 1158 | """Get or set the text representation of sub nodes. 1159 | 1160 | Get the text value:: 1161 | 1162 | >>> doc = PyQuery('<div><span>toto</span><span>tata</span></div>') 1163 | >>> print(doc.text()) 1164 | tototata 1165 | >>> doc = PyQuery('''<div><span>toto</span> 1166 | ... <span>tata</span></div>''') 1167 | >>> print(doc.text()) 1168 | toto tata 1169 | 1170 | Get the text value, without squashing newlines:: 1171 | 1172 | >>> doc = PyQuery('''<div><span>toto</span> 1173 | ... <span>tata</span></div>''') 1174 | >>> print(doc.text(squash_space=False)) 1175 | toto 1176 | tata 1177 | 1178 | Set the text value:: 1179 | 1180 | >>> doc.text('Youhou !') 1181 | [<div>] 1182 | >>> print(doc) 1183 | <div>Youhou !</div> 1184 | 1185 | """ 1186 | 1187 | if value is no_default: 1188 | if not self: 1189 | return '' 1190 | return ' '.join( 1191 | self._copy(tag).html() if tag.tag == 'textarea' else 1192 | extract_text(tag, **kwargs) for tag in self 1193 | ) 1194 | 1195 | for tag in self: 1196 | for child in tag.getchildren(): 1197 | tag.remove(child) 1198 | tag.text = value 1199 | return self 1200 | 1201 | ################ 1202 | # Manipulating # 1203 | ################ 1204 | 1205 | def _get_root(self, value): 1206 | if isinstance(value, basestring): 1207 | root = fromstring(u'<root>' + value + u'</root>', 1208 | self.parser)[0] 1209 | elif isinstance(value, etree._Element): 1210 | root = self._copy(value) 1211 | elif isinstance(value, PyQuery): 1212 | root = value 1213 | else: 1214 | raise TypeError( 1215 | 'Value must be string, PyQuery or Element. Got %r' % value) 1216 | if hasattr(root, 'text') and isinstance(root.text, basestring): 1217 | root_text = root.text 1218 | else: 1219 | root_text = '' 1220 | return root, root_text 1221 | 1222 | def append(self, value): 1223 | """append value to each nodes 1224 | """ 1225 | root, root_text = self._get_root(value) 1226 | for i, tag in enumerate(self): 1227 | if len(tag) > 0: # if the tag has children 1228 | last_child = tag[-1] 1229 | if not last_child.tail: 1230 | last_child.tail = '' 1231 | last_child.tail += root_text 1232 | else: 1233 | if not tag.text: 1234 | tag.text = '' 1235 | tag.text += root_text 1236 | if i > 0: 1237 | root = deepcopy(list(root)) 1238 | tag.extend(root) 1239 | return self 1240 | 1241 | @with_camel_case_alias 1242 | def append_to(self, value): 1243 | """append nodes to value 1244 | """ 1245 | value.append(self) 1246 | return self 1247 | 1248 | def prepend(self, value): 1249 | """prepend value to nodes 1250 | """ 1251 | root, root_text = self._get_root(value) 1252 | for i, tag in enumerate(self): 1253 | if not tag.text: 1254 | tag.text = '' 1255 | if len(root) > 0: 1256 | root[-1].tail = tag.text 1257 | tag.text = root_text 1258 | else: 1259 | tag.text = root_text + tag.text 1260 | if i > 0: 1261 | root = deepcopy(list(root)) 1262 | tag[:0] = root 1263 | root = tag[:len(root)] 1264 | return self 1265 | 1266 | @with_camel_case_alias 1267 | def prepend_to(self, value): 1268 | """prepend nodes to value 1269 | """ 1270 | value.prepend(self) 1271 | return self 1272 | 1273 | def after(self, value): 1274 | """add value after nodes 1275 | """ 1276 | root, root_text = self._get_root(value) 1277 | for i, tag in enumerate(self): 1278 | if not tag.tail: 1279 | tag.tail = '' 1280 | tag.tail += root_text 1281 | if i > 0: 1282 | root = deepcopy(list(root)) 1283 | parent = tag.getparent() 1284 | index = parent.index(tag) + 1 1285 | parent[index:index] = root 1286 | root = parent[index:len(root)] 1287 | return self 1288 | 1289 | @with_camel_case_alias 1290 | def insert_after(self, value): 1291 | """insert nodes after value 1292 | """ 1293 | value.after(self) 1294 | return self 1295 | 1296 | def before(self, value): 1297 | """insert value before nodes 1298 | """ 1299 | root, root_text = self._get_root(value) 1300 | for i, tag in enumerate(self): 1301 | previous = tag.getprevious() 1302 | if previous is not None: 1303 | if not previous.tail: 1304 | previous.tail = '' 1305 | previous.tail += root_text 1306 | else: 1307 | parent = tag.getparent() 1308 | if not parent.text: 1309 | parent.text = '' 1310 | parent.text += root_text 1311 | if i > 0: 1312 | root = deepcopy(list(root)) 1313 | parent = tag.getparent() 1314 | index = parent.index(tag) 1315 | parent[index:index] = root 1316 | root = parent[index:len(root)] 1317 | return self 1318 | 1319 | @with_camel_case_alias 1320 | def insert_before(self, value): 1321 | """insert nodes before value 1322 | """ 1323 | value.before(self) 1324 | return self 1325 | 1326 | def wrap(self, value): 1327 | """A string of HTML that will be created on the fly and wrapped around 1328 | each target: 1329 | 1330 | >>> d = PyQuery('<span>youhou</span>') 1331 | >>> d.wrap('<div></div>') 1332 | [<div>] 1333 | >>> print(d) 1334 | <div><span>youhou</span></div> 1335 | 1336 | """ 1337 | assert isinstance(value, basestring) 1338 | value = fromstring(value)[0] 1339 | nodes = [] 1340 | for tag in self: 1341 | wrapper = deepcopy(value) 1342 | # FIXME: using iterchildren is probably not optimal 1343 | if not wrapper.getchildren(): 1344 | wrapper.append(deepcopy(tag)) 1345 | else: 1346 | childs = [c for c in wrapper.iterchildren()] 1347 | child = childs[-1] 1348 | child.append(deepcopy(tag)) 1349 | nodes.append(wrapper) 1350 | 1351 | parent = tag.getparent() 1352 | if parent is not None: 1353 | for t in parent.iterchildren(): 1354 | if t is tag: 1355 | t.addnext(wrapper) 1356 | parent.remove(t) 1357 | break 1358 | self[:] = nodes 1359 | return self 1360 | 1361 | @with_camel_case_alias 1362 | def wrap_all(self, value): 1363 | """Wrap all the elements in the matched set into a single wrapper 1364 | element:: 1365 | 1366 | >>> d = PyQuery('<div><span>Hey</span><span>you !</span></div>') 1367 | >>> print(d('span').wrap_all('<div id="wrapper"></div>')) 1368 | <div id="wrapper"><span>Hey</span><span>you !</span></div> 1369 | 1370 | >>> d = PyQuery('<div><span>Hey</span><span>you !</span></div>') 1371 | >>> print(d('span').wrapAll('<div id="wrapper"></div>')) 1372 | <div id="wrapper"><span>Hey</span><span>you !</span></div> 1373 | 1374 | .. 1375 | """ 1376 | if not self: 1377 | return self 1378 | 1379 | assert isinstance(value, basestring) 1380 | value = fromstring(value)[0] 1381 | wrapper = deepcopy(value) 1382 | if not wrapper.getchildren(): 1383 | child = wrapper 1384 | else: 1385 | childs = [c for c in wrapper.iterchildren()] 1386 | child = childs[-1] 1387 | 1388 | replace_childs = True 1389 | parent = self[0].getparent() 1390 | if parent is None: 1391 | parent = no_default 1392 | 1393 | # add nodes to wrapper and check parent 1394 | for tag in self: 1395 | child.append(deepcopy(tag)) 1396 | if tag.getparent() is not parent: 1397 | replace_childs = False 1398 | 1399 | # replace nodes i parent if possible 1400 | if parent is not no_default and replace_childs: 1401 | childs = [c for c in parent.iterchildren()] 1402 | if len(childs) == len(self): 1403 | for tag in self: 1404 | parent.remove(tag) 1405 | parent.append(wrapper) 1406 | 1407 | self[:] = [wrapper] 1408 | return self 1409 | 1410 | @with_camel_case_alias 1411 | def replace_with(self, value): 1412 | """replace nodes by value: 1413 | 1414 | >>> doc = PyQuery("<html><div /></html>") 1415 | >>> node = PyQuery("<span />") 1416 | >>> child = doc.find('div') 1417 | >>> child.replace_with(node) 1418 | [<div>] 1419 | >>> print(doc) 1420 | <html><span/></html> 1421 | 1422 | """ 1423 | if isinstance(value, PyQuery): 1424 | value = str(value) 1425 | if hasattr(value, '__call__'): 1426 | for i, element in enumerate(self): 1427 | self._copy(element).before( 1428 | value(i, element) + (element.tail or '')) 1429 | parent = element.getparent() 1430 | parent.remove(element) 1431 | else: 1432 | for tag in self: 1433 | self._copy(tag).before(value + (tag.tail or '')) 1434 | parent = tag.getparent() 1435 | parent.remove(tag) 1436 | return self 1437 | 1438 | @with_camel_case_alias 1439 | def replace_all(self, expr): 1440 | """replace nodes by expr 1441 | """ 1442 | if self._parent is no_default: 1443 | raise ValueError( 1444 | 'replaceAll can only be used with an object with parent') 1445 | self._parent(expr).replace_with(self) 1446 | return self 1447 | 1448 | def clone(self): 1449 | """return a copy of nodes 1450 | """ 1451 | return PyQuery([deepcopy(tag) for tag in self]) 1452 | 1453 | def empty(self): 1454 | """remove nodes content 1455 | """ 1456 | for tag in self: 1457 | tag.text = None 1458 | tag[:] = [] 1459 | return self 1460 | 1461 | def remove(self, expr=no_default): 1462 | """Remove nodes: 1463 | 1464 | >>> h = ( 1465 | ... '<div>Maybe <em>she</em> does <strong>NOT</strong> know</div>' 1466 | ... ) 1467 | >>> d = PyQuery(h) 1468 | >>> d('strong').remove() 1469 | [<strong>] 1470 | >>> print(d) 1471 | <div>Maybe <em>she</em> does know</div> 1472 | """ 1473 | if expr is no_default: 1474 | for tag in self: 1475 | parent = tag.getparent() 1476 | if parent is not None: 1477 | if tag.tail: 1478 | prev = tag.getprevious() 1479 | if prev is None: 1480 | if not parent.text: 1481 | parent.text = '' 1482 | parent.text += tag.tail 1483 | else: 1484 | if not prev.tail: 1485 | prev.tail = '' 1486 | prev.tail += tag.tail 1487 | parent.remove(tag) 1488 | else: 1489 | results = self._copy(expr, self) 1490 | results.remove() 1491 | return self 1492 | 1493 | class Fn(object): 1494 | """Hook for defining custom function (like the jQuery.fn): 1495 | 1496 | .. sourcecode:: python 1497 | 1498 | >>> fn = lambda: this.map(lambda i, el: PyQuery(this).outerHtml()) 1499 | >>> PyQuery.fn.listOuterHtml = fn 1500 | >>> S = PyQuery( 1501 | ... '<ol> <li>Coffee</li> <li>Tea</li> <li>Milk</li> </ol>') 1502 | >>> S('li').listOuterHtml() 1503 | ['<li>Coffee</li>', '<li>Tea</li>', '<li>Milk</li>'] 1504 | 1505 | """ 1506 | def __setattr__(self, name, func): 1507 | def fn(self, *args, **kwargs): 1508 | func.__globals__['this'] = self 1509 | return func(*args, **kwargs) 1510 | fn.__name__ = name 1511 | setattr(PyQuery, name, fn) 1512 | fn = Fn() 1513 | 1514 | ######## 1515 | # AJAX # 1516 | ######## 1517 | 1518 | @with_camel_case_alias 1519 | def serialize_array(self): 1520 | """Serialize form elements as an array of dictionaries, whose structure 1521 | mirrors that produced by the jQuery API. Notably, it does not handle 1522 | the deprecated `keygen` form element. 1523 | 1524 | >>> d = PyQuery('<form><input name="order" value="spam"></form>') 1525 | >>> d.serialize_array() == [{'name': 'order', 'value': 'spam'}] 1526 | True 1527 | >>> d.serializeArray() == [{'name': 'order', 'value': 'spam'}] 1528 | True 1529 | """ 1530 | return list(map( 1531 | lambda p: {'name': p[0], 'value': p[1]}, 1532 | self.serialize_pairs() 1533 | )) 1534 | 1535 | def serialize(self): 1536 | """Serialize form elements as a URL-encoded string. 1537 | 1538 | >>> h = ( 1539 | ... '<form><input name="order" value="spam">' 1540 | ... '<input name="order2" value="baked beans"></form>' 1541 | ... ) 1542 | >>> d = PyQuery(h) 1543 | >>> d.serialize() 1544 | 'order=spam&order2=baked%20beans' 1545 | """ 1546 | return urlencode(self.serialize_pairs()).replace('+', '%20') 1547 | 1548 | ##################################################### 1549 | # Additional methods that are not in the jQuery API # 1550 | ##################################################### 1551 | 1552 | @with_camel_case_alias 1553 | def serialize_pairs(self): 1554 | """Serialize form elements as an array of 2-tuples conventional for 1555 | typical URL-parsing operations in Python. 1556 | 1557 | >>> d = PyQuery('<form><input name="order" value="spam"></form>') 1558 | >>> d.serialize_pairs() 1559 | [('order', 'spam')] 1560 | >>> d.serializePairs() 1561 | [('order', 'spam')] 1562 | """ 1563 | # https://github.com/jquery/jquery/blob 1564 | # /2d4f53416e5f74fa98e0c1d66b6f3c285a12f0ce/src/serialize.js#L14 1565 | _submitter_types = ['submit', 'button', 'image', 'reset', 'file'] 1566 | 1567 | controls = self._copy([]) 1568 | # Expand list of form controls 1569 | for el in self.items(): 1570 | if el[0].tag == 'form': 1571 | form_id = el.attr('id') 1572 | if form_id: 1573 | # Include inputs outside of their form owner 1574 | root = self._copy(el.root.getroot()) 1575 | controls.extend(root( 1576 | '#%s :not([form]):input, [form="%s"]:input' 1577 | % (form_id, form_id))) 1578 | else: 1579 | controls.extend(el(':not([form]):input')) 1580 | elif el[0].tag == 'fieldset': 1581 | controls.extend(el(':input')) 1582 | else: 1583 | controls.extend(el) 1584 | # Filter controls 1585 | selector = '[name]:enabled:not(button)' # Not serializing image button 1586 | selector += ''.join(map( 1587 | lambda s: ':not([type="%s"])' % s, 1588 | _submitter_types)) 1589 | controls = controls.filter(selector) 1590 | 1591 | def _filter_out_unchecked(_, el): 1592 | el = controls._copy(el) 1593 | return not el.is_(':checkbox:not(:checked)') and \ 1594 | not el.is_(':radio:not(:checked)') 1595 | controls = controls.filter(_filter_out_unchecked) 1596 | 1597 | # jQuery serializes inputs with the datalist element as an ancestor 1598 | # contrary to WHATWG spec as of August 2018 1599 | # 1600 | # xpath = 'self::*[not(ancestor::datalist)]' 1601 | # results = [] 1602 | # for tag in controls: 1603 | # results.extend(tag.xpath(xpath, namespaces=controls.namespaces)) 1604 | # controls = controls._copy(results) 1605 | 1606 | # Serialize values 1607 | ret = [] 1608 | for field in controls: 1609 | val = self._copy(field).val() or '' 1610 | if isinstance(val, list): 1611 | ret.extend(map( 1612 | lambda v: (field.attrib['name'], v.replace('\n', '\r\n')), 1613 | val 1614 | )) 1615 | else: 1616 | ret.append((field.attrib['name'], val.replace('\n', '\r\n'))) 1617 | return ret 1618 | 1619 | @with_camel_case_alias 1620 | def serialize_dict(self): 1621 | """Serialize form elements as an ordered dictionary. Multiple values 1622 | corresponding to the same input name are concatenated into one list. 1623 | 1624 | >>> d = PyQuery('''<form> 1625 | ... <input name="order" value="spam"> 1626 | ... <input name="order" value="eggs"> 1627 | ... <input name="order2" value="ham"> 1628 | ... </form>''') 1629 | >>> d.serialize_dict() 1630 | OrderedDict({'order': ['spam', 'eggs'], 'order2': 'ham'}) 1631 | >>> d.serializeDict() 1632 | OrderedDict({'order': ['spam', 'eggs'], 'order2': 'ham'}) 1633 | """ 1634 | ret = OrderedDict() 1635 | for name, val in self.serialize_pairs(): 1636 | if name not in ret: 1637 | ret[name] = val 1638 | elif not isinstance(ret[name], list): 1639 | ret[name] = [ret[name], val] 1640 | else: 1641 | ret[name].append(val) 1642 | return ret 1643 | 1644 | @property 1645 | def base_url(self): 1646 | """Return the url of current html document or None if not available. 1647 | """ 1648 | if self._base_url is not None: 1649 | return self._base_url 1650 | if self._parent is not no_default: 1651 | return self._parent.base_url 1652 | 1653 | def make_links_absolute(self, base_url=None): 1654 | """Make all links absolute. 1655 | """ 1656 | if base_url is None: 1657 | base_url = self.base_url 1658 | if base_url is None: 1659 | raise ValueError(( 1660 | 'You need a base URL to make your links' 1661 | 'absolute. It can be provided by the base_url parameter.')) 1662 | 1663 | def repl(attr): 1664 | def rep(i, e): 1665 | attr_value = self(e).attr(attr) 1666 | # when label hasn't such attr, pass 1667 | if attr_value is None: 1668 | return None 1669 | 1670 | # skip specific "protocol" schemas 1671 | if any(attr_value.startswith(schema) 1672 | for schema in ('tel:', 'callto:', 'sms:')): 1673 | return None 1674 | 1675 | return self(e).attr(attr, 1676 | urljoin(base_url, attr_value.strip())) 1677 | return rep 1678 | 1679 | self('a').each(repl('href')) 1680 | self('link').each(repl('href')) 1681 | self('script').each(repl('src')) 1682 | self('img').each(repl('src')) 1683 | self('iframe').each(repl('src')) 1684 | self('form').each(repl('action')) 1685 | 1686 | return self 1687 | 1688 | 1689 | build_camel_case_aliases(PyQuery) 1690 | --------------------------------------------------------------------------------