├── wp2md ├── __init__.py ├── __main__.py ├── version.py ├── authoring.py ├── wp2md.py └── html2text.py ├── .gitignore ├── .editorconfig ├── setup.py ├── README.md └── LICENSE /wp2md/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /wp2md/__main__.py: -------------------------------------------------------------------------------- 1 | import sys 2 | from .wp2md import main 3 | 4 | sys.exit(main()) 5 | -------------------------------------------------------------------------------- /wp2md/version.py: -------------------------------------------------------------------------------- 1 | # coding: utf-8 2 | 3 | __version_info__ = (0, 8, 1) 4 | __version__ = '.'.join(map(str, __version_info__)) 5 | 6 | 7 | def get_version(): 8 | return __version__ 9 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | *.py[co] 2 | *.log 3 | 4 | ; Python packaging 5 | bin 6 | build 7 | dist 8 | sdist 9 | MANIFEST 10 | *.egg-info 11 | 12 | ; Wordpress exported data 13 | *.xml 14 | 15 | ; Generated files 16 | out/* 17 | -------------------------------------------------------------------------------- /wp2md/authoring.py: -------------------------------------------------------------------------------- 1 | # coding: utf-8 2 | 3 | __author__ = 'Alex Musayev' 4 | __email__ = 'alex.musayev@gmail.com' 5 | __copyright__ = "Copyright 2012, %s " % __author__ 6 | __license__ = 'GNU GPL 3' 7 | __status__ = 'Development' 8 | __url__ = 'http://github.com/dreikanter/wp2md' 9 | -------------------------------------------------------------------------------- /.editorconfig: -------------------------------------------------------------------------------- 1 | ; top-most EditorConfig file 2 | root = true 3 | 4 | ; Unix-style newlines 5 | [*] 6 | end_of_line = CRLF 7 | 8 | ; 4 space indentation 9 | [*.py] 10 | indent_style = space 11 | indent_size = 4 12 | 13 | ; Tab indentation (no size specified) 14 | [*.js] 15 | indent_style = tab 16 | 17 | ; Indentation override for all JS under lib directory 18 | [lib/**.js] 19 | indent_style = space 20 | indent_size = 2 21 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # coding: utf-8 3 | 4 | from setuptools import setup, find_packages 5 | import sys 6 | import wp2md.authoring 7 | from wp2md.version import get_version 8 | 9 | setup( 10 | name='wp2md', 11 | description='A script to convert Wordpress XML dumps to plain text/markdown files.', 12 | version=get_version(), 13 | license=wp2md.authoring.__license__, 14 | author=wp2md.authoring.__author__, 15 | author_email=wp2md.authoring.__email__, 16 | url=wp2md.authoring.__url__, 17 | long_description=open('README.md',"rb").read().decode('utf8'), 18 | platforms=['any'], 19 | packages=find_packages(), 20 | install_requires=[ 21 | 'markdown', 22 | 'html2text' 23 | ], 24 | entry_points={'console_scripts': ['wp2md = wp2md.wp2md:main']}, 25 | include_package_data=True, 26 | zip_safe=False, 27 | classifiers=[ 28 | 'Development Status :: 5 - Production/Stable', 29 | 'Intended Audience :: Developers', 30 | 'License :: OSI Approved :: GNU General Public License (GPL)', 31 | 'Programming Language :: Python', 32 | 'Programming Language :: Python :: 2.7', 33 | 'Programming Language :: Python :: 3.3', 34 | ], 35 | dependency_links=[ 36 | 'https://github.com/aaronsw/html2text/tarball/master#egg=html2text' 37 | ], 38 | ) 39 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # WordPress to Markdown Exporter 2 | 3 | > **Update:** I don't have much time to maintain this project, but I would really appreciate community help. If you looking for an open source project to contribute, it's a great opportunity. Pull request a very appreciated by me and migrating WordPress users. 4 | 5 | A python script to convert WordPress XML dump to a set of plain text/[markdown](http://daringfireball.net/projects/markdown) files. Intended to be used for migration from WordPress to [public-static](http://github.com/dreikanter/public-static) website generator, but could also be helpful as general purpose WordPress content processor. 6 | 7 | 8 | ## Installation 9 | 10 | The script could be installed by command: 11 | 12 | pip install git+https://github.com/dreikanter/wp2md 13 | 14 | It will install wp2md and the following dependencies: 15 | 16 | * [html2text](https://github.com/aaronsw/html2text/) 17 | * [python-markdown](http://pypi.python.org/pypi/Markdown/) 18 | 19 | 20 | ## Usage 21 | 22 | [Export](http://en.support.wordpress.com/export/) WordPress data to XML file (Tools → Export → All content): 23 | 24 | ![WordPress content export](http://img-fotki.yandex.ru/get/6403/988666.0/0_a05db_af845b23_L.jpg) 25 | 26 | And then run the following command: 27 | 28 | wp2md -d /export/path/ wordpress-dump.xml 29 | 30 | Where `/export/path/` is the directory where post and page files will be generated, and `wordpress-dump.xml` is the XML file exported by WordPress. 31 | 32 | Use `--help` parameter to see the complete list of command line options: 33 | 34 | usage: wp2md [options] source 35 | 36 | Export WordPress XML dump to markdown files 37 | 38 | positional arguments: 39 | source source XML dump exported from WordPress 40 | 41 | optional arguments: 42 | -h, --help show this help message and exit 43 | -v verbose logging 44 | -l FILE log to file 45 | -d PATH destination path for generated files 46 | -u FMT date/time parsing format 47 | -o FMT and parsing format 48 | -f FMT date/time fields format for exported data 49 | -p FMT date prefix format for generated files 50 | -m preprocess content with Markdown (helpful for MD input) 51 | -n LEN post name (slug) length limit for file naming 52 | -r generate reference links instead of inline 53 | -ps PATH post files path (see docs for variable names) 54 | -pg PATH page files path 55 | -dr PATH draft files path 56 | -url keep absolute URLs in hrefs and image srcs 57 | -b URL base URL to subtract from hrefs (default is the root) 58 | 59 | 60 | ## The output 61 | 62 | The script generates a separate file for each post, page and draft, and groups it by configurable directory structure. By default posts are grouped by year-named directories and pages are just stored to the output folder. 63 | 64 | ![Exported files](http://img-fotki.yandex.ru/get/6500/988666.0/0_a05da_66f67f9f_L.jpg) 65 | 66 | But you could specify different directory structure and file naming pattern using `-ps`, `-pg` and `-dr` parameters for posts, pages and drafts respectively. For example `-ps {year}/{month}/{day}/{title}.md` will produce date-based subfolders for blog posts. 67 | 68 | Each exported file has a straightforward structure intended for further processing with [public-static](http://github.com/dreikanter/public-static) website generator. It has an INI-like formatted header followed by markdown-formatted post (or page) contents: 69 | 70 | title: Я.Субботник в Санкт-Петербурге, 3 декабря 71 | link: http://paradigm.ru/yandex-subbotni 72 | creator: admin 73 | description: 74 | post_id: 635 75 | post_date: 2011-11-23 22:10:35 76 | post_date_gmt: 2011-11-23 19:10:35 77 | comment_status: open 78 | post_name: yandex-subbotnik 79 | status: publish 80 | post_type: post 81 | 82 | # Я.Субботник в Санкт-Петербурге, 3 декабря 83 | 84 | Я.Субботник в Санкт-Петербурге пройдет 3 декабря в [офисе Яндекса](http://company.yandex.ru/contacts/spb/). 85 | ... 86 | 87 | If the post contains comments, they will be included below. 88 | 89 | 90 | ## See also 91 | 92 | * How to [export WordPress data](http://codex.wordpress.org/Tools_Export_Screen) 93 | * How to [export Wordpress.com data](http://en.support.wordpress.com/export/) 94 | * [Wordpress to Hugo exporter](https://github.com/SchumacherFM/wordpress-to-hugo-exporter) 95 | 96 | 97 | ## Copyright and licensing 98 | 99 | Copyright © 2013 by [Alex Musayev](http://alex.musayev.com). 100 | License: GNU (see [LICENSE](https://raw.github.com/dreikanter/wp2md/master/LICENSE)). 101 | 102 | Project home: [https://github.com/dreikanter/wp2md](https://github.com/dreikanter/wp2md). 103 | -------------------------------------------------------------------------------- /wp2md/wp2md.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | """A script to convert Wordpress XML dumps to plain text/markdown files.""" 3 | 4 | import argparse 5 | import codecs 6 | import datetime 7 | import logging 8 | import markdown 9 | import os.path 10 | import re 11 | import sys 12 | import time 13 | import traceback 14 | from xml.etree.ElementTree import XMLParser 15 | from . import html2text 16 | 17 | PY2 = sys.version_info[0] == 2 18 | 19 | str_t = unicode if PY2 else str 20 | 21 | # XML elements to save (starred ones are additional fields 22 | # generated during export data processing) 23 | WHAT2SAVE = { 24 | 'channel': [ 25 | 'title', 26 | 'description', 27 | 'author_display_name', 28 | 'author_login', 29 | 'author_email', 30 | 'base_site_url', 31 | 'base_blog_url', 32 | 'export_date', # Generated: data export timestamp 33 | 'content', # Generated: items list 34 | # 'link', 35 | # 'language', 36 | ], 37 | 'item': [ 38 | 'title', 39 | 'link', 40 | 'creator', 41 | 'description', 42 | 'post_id', 43 | 'post_date', 44 | 'post_date_gmt', 45 | 'comment_status', 46 | 'post_name', 47 | 'status', 48 | 'post_type', 49 | 'excerpt', 50 | 'content', # Generated: item content 51 | 'comments', # Generated: comments lis 52 | # 'guid', 53 | # 'is_sticky', 54 | # 'menu_order', 55 | # 'ping_status', 56 | # 'post_parent', 57 | # 'post_password', 58 | ], 59 | 'comment': [ 60 | 'comment_id', 61 | 'comment_author', 62 | 'comment_author_email', 63 | 'comment_author_url', 64 | 'comment_author_IP', 65 | 'comment_date', 66 | 'comment_date_gmt', 67 | 'comment_content', 68 | 'comment_approved', 69 | 'comment_type', 70 | # 'comment_parent', 71 | # 'comment_user_id', 72 | ], 73 | } 74 | 75 | # Wordpress RSS items to public-static page header fields mapping 76 | # (undefined names will remain unchanged) 77 | FIELD_MAP = { 78 | 'creator': 'author', 79 | 'post_date': 'created', 80 | 'post_date_gmt': 'created_gmt', 81 | } 82 | 83 | DEFAULT_MAX_NAME_LEN = 50 84 | UNTITLED = 'untitled' 85 | MD_URL_RE = None 86 | 87 | log = logging.getLogger(__name__) 88 | conf = {} 89 | stats = { 90 | 'page': 0, 91 | 'post': 0, 92 | 'comment': 0, 93 | } 94 | 95 | 96 | # Configuration and logging 97 | 98 | def init(): 99 | global conf 100 | args = parse_args() 101 | init_logging(args.l, args.v) 102 | conf = { 103 | 'source_file': args.source, 104 | 'dump_path': args.d, 105 | 'page_path': args.pg, 106 | 'post_path': args.ps, 107 | 'draft_path': args.dr, 108 | 'verbose': args.v, 109 | 'parse_date_fmt': args.u, 110 | 'post_date_fmt': args.o, 111 | 'date_fmt': args.f, 112 | 'page_date_fmt': args.ef, 113 | 'file_date_fmt': args.p, 114 | 'log_file': args.l, 115 | 'md_input': args.m, 116 | 'max_name_len': args.n, 117 | 'ref_links': args.r, 118 | 'fix_urls': args.url, 119 | 'base_url': args.b, 120 | } 121 | 122 | try: 123 | value = int(conf['max_name_len']) 124 | if value < 0 or value > 100: 125 | raise ValueError() 126 | conf['max_name_len'] = value 127 | except: 128 | log.warn('Bad post name length limitation value. Using default.') 129 | conf['max_name_len'] = DEFAULT_MAX_NAME_LEN 130 | 131 | 132 | def init_logging(log_file, verbose): 133 | try: 134 | global log 135 | log.setLevel(logging.DEBUG) 136 | log_level = logging.DEBUG if verbose else logging.INFO 137 | 138 | channel = logging.StreamHandler() 139 | channel.setLevel(log_level) 140 | fmt = '%(message)s' 141 | channel.setFormatter(logging.Formatter(fmt)) 142 | log.addHandler(channel) 143 | 144 | if log_file: 145 | channel = logging.FileHandler(log_file) 146 | channel.setLevel(logging.DEBUG) 147 | fmt = '%(asctime)s %(levelname)s: %(message)s' 148 | channel.setFormatter(logging.Formatter(fmt, '%H:%M:%S')) 149 | log.addHandler(channel) 150 | 151 | except Exception as e: 152 | log.debug(traceback.format_exc()) 153 | raise Exception(getxm('Logging initialization failed', e)) 154 | 155 | 156 | def parse_args(): 157 | desc = __doc__.split('\n\n')[0] 158 | parser = argparse.ArgumentParser(description=desc) 159 | parser.add_argument( 160 | '-v', 161 | action='store_true', 162 | default=False, 163 | help='verbose logging') 164 | parser.add_argument( 165 | '-l', 166 | action='store', 167 | metavar='FILE', 168 | default=None, 169 | help='log to file') 170 | parser.add_argument( 171 | '-d', 172 | action='store', 173 | metavar='PATH', 174 | default='{year}{month}{day}_{source}', 175 | help='destination path for generated files') 176 | parser.add_argument( 177 | '-u', 178 | action='store', 179 | metavar='FMT', 180 | default="%a, %d %b %Y %H:%M:%S +0000", 181 | help=' date/time parsing format') 182 | parser.add_argument( 183 | '-o', 184 | action='store', 185 | metavar='FMT', 186 | default="%Y %H:%M:%S", 187 | help=' and parsing format') 188 | parser.add_argument( 189 | '-f', 190 | action='store', 191 | metavar='FMT', 192 | default="%Y-%m-%d %H:%M:%S", 193 | help='date/time fields parsing format for input data') 194 | parser.add_argument( 195 | '-ef', 196 | action='store', 197 | metavar='FMT', 198 | default="%Y/%m/%d %H:%M:%S", 199 | help='date/time fields format for generated pages') 200 | parser.add_argument( 201 | '-p', 202 | action='store', 203 | metavar='FMT', 204 | default="%Y%m%d", 205 | help='date prefix format for generated files') 206 | parser.add_argument( 207 | '-m', 208 | action='store_true', 209 | default=False, 210 | help='preprocess content with Markdown (helpful for MD input)') 211 | parser.add_argument( 212 | '-n', 213 | action='store', 214 | metavar='LEN', 215 | default=DEFAULT_MAX_NAME_LEN, 216 | help='post name (slug) length limit for file naming') 217 | parser.add_argument( 218 | '-r', 219 | action='store_true', 220 | default=False, 221 | help='generate reference links instead of inline') 222 | parser.add_argument( 223 | '-ps', 224 | action='store', 225 | metavar='PATH', 226 | default=os.path.join("posts", "{year}{month}{day}-{name}.md"), 227 | help='post files path (see docs for variable names)') 228 | parser.add_argument( 229 | '-pg', 230 | action='store', 231 | metavar='PATH', 232 | default=os.path.join("pages", "{name}.md"), 233 | help='page files path') 234 | parser.add_argument( 235 | '-dr', 236 | action='store', 237 | metavar='PATH', 238 | default="drafts/{name}.md", 239 | help='draft files path') 240 | parser.add_argument( 241 | '-url', 242 | action='store_false', 243 | default=True, 244 | help="keep absolute URLs in hrefs and image srcs") 245 | parser.add_argument( 246 | '-b', 247 | action='store', 248 | metavar='URL', 249 | default=None, 250 | help='base URL to subtract from hrefs (default is the root)') 251 | parser.add_argument( 252 | 'source', 253 | action='store', 254 | help='source XML dump exported from Wordpress') 255 | return parser.parse_args(sys.argv[1:]) 256 | 257 | 258 | # Helpers 259 | 260 | def getxm(message, exception): 261 | """Returns annotated exception messge.""" 262 | return ("%s: %s" % (message, str(exception))) if exception else message 263 | 264 | 265 | def tag_name(name): 266 | """Removes expanded namespace from tag name.""" 267 | result = name[name.find('}') + 1:] 268 | if result == 'encoded': 269 | if name.find('/content/') > -1: 270 | result = 'content' 271 | elif name.find('/excerpt/') > -1: 272 | result = 'excerpt' 273 | return result 274 | 275 | 276 | def parse_date(date_str, format, default=None): 277 | """Parses date string according to specified format.""" 278 | try: 279 | result = time.strptime(date_str, format) 280 | except: 281 | msg = "Error parsing date string '%s'. Using default value." % date_str 282 | log.debug(msg) 283 | result = default 284 | 285 | return result 286 | 287 | 288 | def get_path_fmt(item_type, data): 289 | """Returns preconfigured export path format for specified 290 | RSS item type and metadata.""" 291 | 292 | if data.get('status', None).lower() == 'draft': 293 | return conf['draft_path'] 294 | is_post = item_type == 'post' 295 | return conf['post_path'] if is_post else conf['page_path'] 296 | 297 | 298 | def get_path(item_type, file_name=None, data=None): 299 | """Generates full path for the generated file using configuration 300 | and explicitly specified name or RSS item data. At least one argument 301 | should be specified. @file_name has higher priority during output 302 | path generation. 303 | 304 | Arguments: 305 | item_type -- 'post' or 'page' 306 | file_name -- explicitly defined correct file name. 307 | data -- preprocessed RSS item data dictionary.""" 308 | 309 | if not file_name and type(data) is not dict: 310 | raise Exception('File name or RSS item data dict should be defined') 311 | 312 | root = conf['dump_path'] 313 | root = root.format(date=time.strftime(conf['file_date_fmt']), 314 | year=time.strftime("%Y"), 315 | month=time.strftime("%m"), 316 | day=time.strftime("%d"), 317 | source=os.path.basename(conf['source_file'])) 318 | 319 | if file_name: 320 | relpath = file_name 321 | else: 322 | name = data.get('post_name', '').strip() 323 | name = name or data.get('post_id', UNTITLED) 324 | relpath = get_path_fmt(item_type, data) 325 | field = FIELD_MAP.get('post_date', 'post_date') 326 | post_date = data[field] 327 | relpath = relpath.format(year=time.strftime("%Y", post_date), 328 | month=time.strftime("%m", post_date), 329 | day=time.strftime("%d", post_date), 330 | name=name, 331 | title=name) 332 | 333 | return uniquify(os.path.join(os.path.abspath(root), relpath)) 334 | 335 | 336 | def uniquify(file_name): 337 | """Inserts numeric suffix at the end of file name to make 338 | it's name unique in the directory.""" 339 | 340 | suffix = 0 341 | result = file_name 342 | while True: 343 | if os.path.exists(result): 344 | suffix += 1 345 | result = insert_suffix(file_name, suffix) 346 | else: 347 | return result 348 | 349 | 350 | def insert_suffix(file_name, suffix): 351 | """Inserts suffix to the end of file name (before extension). 352 | If suffix is zero (or False in boolean representation), nothing 353 | will be inserted. 354 | 355 | Usage: 356 | >>> insert_suffix('c:/temp/hello.txt', 2) 357 | c:/temp/hello-2.txt 358 | >>> insert_suffix('readme.txt', 0) 359 | readme.txt 360 | 361 | Intended to be used for numeric suffixes for file 362 | name uniquification (what a word!).""" 363 | 364 | if not suffix: 365 | return file_name 366 | base, ext = os.path.splitext(file_name) 367 | return "%s-%s%s" % (base, suffix, ext) 368 | 369 | 370 | # Markdown processing and generation 371 | 372 | def html2md(html): 373 | h2t = html2text.HTML2Text() 374 | h2t.unicode_snob = True 375 | h2t.inline_links = not conf['ref_links'] 376 | h2t.body_width = 0 377 | return h2t.handle(html).strip() 378 | 379 | 380 | def generate_toc(meta, items): 381 | """Generates MD-formatted index page.""" 382 | if not meta.get('description', ''): 383 | content = '\n\n' 384 | else: 385 | content = meta.get('description', '') + '\n\n' 386 | for item in items: 387 | content += str_t("* {post_date}: [{title}]({link})\n").format(**item) 388 | return content 389 | 390 | 391 | def generate_comments(comments): 392 | """Generates MD-formatted comments list from parsed data.""" 393 | 394 | result = str_t('') 395 | for comment in comments: 396 | try: 397 | approved = comment['comment_approved'] == '1' 398 | pingback = comment.get('comment_type', '').lower() == 'pingback' 399 | if approved and not pingback: 400 | cmfmt = str_t("**[{author}](#{id} \"{timestamp}\"):** {content}\n\n") 401 | content = html2md(comment['comment_content']) 402 | result += cmfmt.format(id=comment['comment_id'], 403 | timestamp=comment['comment_date'], 404 | author=comment['comment_author'], 405 | content=content) 406 | except: 407 | # Ignore malformed data 408 | pass 409 | 410 | return result and str_t("## Comments\n\n" + result) 411 | 412 | 413 | def fix_urls(text): 414 | """Removes base_url prefix from MD links and image sources.""" 415 | global MD_URL_RE 416 | if MD_URL_RE is None: 417 | base_url = re.escape(conf['base_url']) 418 | MD_URL_RE = re.compile(r'\]\(%s(.*)\)' % base_url) 419 | return MD_URL_RE.sub(r'](\1)', text) 420 | 421 | 422 | # Statistics 423 | 424 | def stopwatch_set(): 425 | """Starts stopwatch timer.""" 426 | globals()['_stopwatch_start_time'] = datetime.datetime.now() 427 | 428 | 429 | def stopwatch_get(): 430 | """Returns string representation for elapsed time since last 431 | stopwatch_set() call.""" 432 | delta = datetime.datetime.now() - globals().get('_stopwatch_start_time', 0) 433 | delta = str(delta).strip('0:') 434 | return ('0' + delta) if delta[0] == '.' else delta 435 | 436 | 437 | def statplusplus(field, value=1): 438 | global stats 439 | if field in stats: 440 | stats[field] += value 441 | else: 442 | raise ValueError("Illegal name for stats field: " + str(field)) 443 | 444 | 445 | # Parser data handlers 446 | 447 | def dump_channel(meta, items): 448 | """Dumps RSS channel metadata and items index.""" 449 | file_name = get_path('page', 'index.md') 450 | log.info("Dumping index to '%s'" % file_name) 451 | fields = WHAT2SAVE['channel'] 452 | meta = {field: meta.get(field, None) for field in fields} 453 | 454 | # Append export_date 455 | pub_date = meta.get('pubDate', None) 456 | format = conf['parse_date_fmt'] 457 | meta['export_date'] = parse_date(pub_date, format, time.gmtime()) 458 | 459 | # Append table of contents 460 | meta['content'] = generate_toc(meta, items) 461 | 462 | dump(file_name, meta, fields) 463 | 464 | 465 | def dump_item(data): 466 | """Dumps RSS channel item.""" 467 | if not 'post_type' in data: 468 | log.error('Malformed RSS item: item type is not specified.') 469 | return 470 | 471 | item_type = data['post_type'] 472 | if item_type not in ['post', 'page', 'draft']: 473 | return 474 | 475 | fields = WHAT2SAVE['item'] 476 | pdata = {} 477 | for field in fields: 478 | pdata[FIELD_MAP.get(field, field)] = data.get(field, '') 479 | 480 | # Post date 481 | format = conf['date_fmt'] 482 | field = FIELD_MAP.get('post_date', 'post_date') 483 | value = pdata.get(field, None) 484 | pdata[field] = value and parse_date(value, format, None) 485 | 486 | # Post date GMT 487 | field = FIELD_MAP.get('post_date_gmt', 'post_date_gmt') 488 | value = pdata.get(field, None) 489 | pdata[field] = value and parse_date(value, format, None) 490 | 491 | dump_path = get_path(item_type, data=pdata) 492 | log.info("Dumping %s to '%s'" % (item_type, dump_path)) 493 | 494 | fields = [FIELD_MAP.get(field, field) for field in fields] 495 | dump(dump_path, pdata, fields) 496 | 497 | statplusplus(item_type) 498 | if 'comments' in data: 499 | statplusplus('comment', len(data['comments'])) 500 | 501 | 502 | def dump(file_name, data, order): 503 | """Dumps a dictionary to YAML-like text file.""" 504 | try: 505 | dir_path = os.path.dirname(os.path.abspath(file_name)) 506 | if dir_path and not os.path.exists(dir_path): 507 | os.makedirs(dir_path) 508 | 509 | with codecs.open(file_name, 'w', 'utf-8') as f: 510 | extras = {} 511 | for field in filter(lambda x: x in data, [item for item in order]): 512 | if field in ['content', 'comments', 'excerpt']: 513 | # Fields for non-standard processing 514 | extras[field] = data[field] 515 | else: 516 | if type(data[field]) == time.struct_time: 517 | value = time.strftime(conf['page_date_fmt'], data[field]) 518 | else: 519 | value = data[field] or '' 520 | f.write(str_t("%s: %s\n") % (str_t(field), str_t(value))) 521 | 522 | if extras: 523 | excerpt = extras.get('excerpt', '') 524 | excerpt = excerpt and '' % excerpt 525 | 526 | content = extras.get('content', '') 527 | if conf['md_input']: 528 | # Using new MD instance works 3x faster than 529 | # reusing existing one for some reason 530 | md = markdown.Markdown(extensions=[]) 531 | content = md.convert(content) 532 | 533 | if conf['fix_urls']: 534 | content = fix_urls(html2md(content)) 535 | 536 | if 'title' in data: 537 | content = str_t("# %s\n\n%s") % (data['title'], content) 538 | 539 | comments = generate_comments(extras.get('comments', [])) 540 | extras = filter(None, [excerpt, content, comments]) 541 | f.write('\n' + '\n\n'.join(extras)) 542 | 543 | except Exception as e: 544 | log.error("Error saving data to '%s'" % (file_name)) 545 | log.debug(e) 546 | 547 | 548 | def store_base_url(channel): 549 | """Stores base URL in configuration if it's not defined explicitly.""" 550 | if conf['fix_urls'] and not conf['base_url']: 551 | conf['base_url'] = channel.get('base_site_url', '') 552 | 553 | 554 | # The Parser 555 | 556 | class CustomParser: 557 | def __init__(self): 558 | self.section_stack = [] 559 | self.channel = {} 560 | self.items = [] 561 | self.item = None 562 | self.cmnt = None 563 | self.subj = None 564 | 565 | def start(self, tag, attrib): 566 | tag = tag_name(tag) 567 | if tag == 'channel': 568 | self.start_section('channel') 569 | 570 | elif tag == 'item': 571 | self.item = {'comments': []} 572 | self.start_section('item') 573 | 574 | elif self.item and tag == 'comment': 575 | self.cmnt = {} 576 | self.start_section('comment') 577 | 578 | elif self.cur_section(): 579 | self.subj = tag 580 | 581 | else: 582 | self.subj = None 583 | 584 | def end(self, tag): 585 | tag = tag_name(tag) 586 | if tag == 'comment' and self.cur_section() == 'comment': 587 | self.end_section() 588 | self.item['comments'].append(self.cmnt) 589 | self.cmnt = None 590 | 591 | elif tag == 'item' and self.cur_section() == 'item': 592 | self.end_section() 593 | dump_item(self.item) 594 | self.store_item_info() 595 | self.item = None 596 | 597 | elif tag == 'channel': 598 | self.end_section() 599 | dump_channel(self.channel, self.items) 600 | 601 | elif self.cur_section(): 602 | self.subj = None 603 | 604 | def data(self, data): 605 | if self.subj: 606 | if self.cur_section() == 'comment': 607 | self.cmnt[self.subj] = data 608 | 609 | elif self.cur_section() == 'item': 610 | self.item[self.subj] = data 611 | 612 | elif self.cur_section() == 'channel': 613 | self.channel[self.subj] = data 614 | if self.subj == 'base_site_url': 615 | store_base_url(self.channel) 616 | self.subj = None 617 | 618 | def start_section(self, what): 619 | self.section_stack.append(what) 620 | 621 | def end_section(self): 622 | if len(self.section_stack): 623 | self.section_stack.pop() 624 | 625 | def cur_section(self): 626 | try: 627 | return self.section_stack[-1] 628 | except: 629 | return None 630 | 631 | def store_item_info(self): 632 | post_type = self.item.get('post_type', '').lower() 633 | if not post_type in ['post', 'page']: 634 | return 635 | 636 | fields = [ 637 | 'title', 638 | 'link', 639 | 'post_id', 640 | 'post_date', 641 | 'post_type', 642 | ] 643 | 644 | self.items.append({}) 645 | for field in fields: 646 | self.items[-1][field] = self.item.get(field, None) 647 | 648 | 649 | def main(): 650 | init() 651 | log.info("Parsing '%s'..." % os.path.basename(conf['source_file'])) 652 | 653 | stopwatch_set() 654 | target = CustomParser() 655 | parser = XMLParser(target=target) 656 | if PY2: 657 | text = open(conf['source_file']).read() 658 | else: 659 | text = codecs.open(conf['source_file'], encoding='utf-8').read() 660 | parser.feed(text) 661 | 662 | log.info('') 663 | totals = 'Total: posts: {post}; pages: {page}; comments: {comment}' 664 | log.info(totals.format(**stats)) 665 | log.info('Elapsed time: %s s' % stopwatch_get()) 666 | 667 | 668 | if __name__ == '__main__': 669 | main() 670 | -------------------------------------------------------------------------------- /wp2md/html2text.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | """html2text: Turn HTML into equivalent Markdown-structured text.""" 3 | __version__ = "3.200.3" 4 | __author__ = "Aaron Swartz (me@aaronsw.com)" 5 | __copyright__ = "(C) 2004-2008 Aaron Swartz. GNU GPL 3." 6 | __contributors__ = ["Martin 'Joey' Schulze", "Ricardo Reyes", "Kevin Jay North"] 7 | 8 | # TODO: 9 | # Support decoded entities with unifiable. 10 | 11 | try: 12 | True 13 | except NameError: 14 | setattr(__builtins__, 'True', 1) 15 | setattr(__builtins__, 'False', 0) 16 | 17 | def has_key(x, y): 18 | if hasattr(x, 'has_key'): return x.has_key(y) 19 | else: return y in x 20 | 21 | try: 22 | import htmlentitydefs 23 | import urlparse 24 | import HTMLParser 25 | except ImportError: #Python3 26 | import html.entities as htmlentitydefs 27 | import urllib.parse as urlparse 28 | import html.parser as HTMLParser 29 | try: #Python3 30 | import urllib.request as urllib 31 | except: 32 | import urllib 33 | import optparse, re, sys, codecs, types 34 | 35 | try: from textwrap import wrap 36 | except: pass 37 | 38 | import sys 39 | 40 | PY2 = sys.version_info[0] == 2 41 | 42 | strtype = unicode if PY2 else str 43 | 44 | # Use Unicode characters instead of their ascii psuedo-replacements 45 | UNICODE_SNOB = 0 46 | 47 | # Escape all special characters. Output is less readable, but avoids corner case formatting issues. 48 | ESCAPE_SNOB = 0 49 | 50 | # Put the links after each paragraph instead of at the end. 51 | LINKS_EACH_PARAGRAPH = 0 52 | 53 | # Wrap long lines at position. 0 for no wrapping. (Requires Python 2.3.) 54 | BODY_WIDTH = 78 55 | 56 | # Don't show internal links (href="#local-anchor") -- corresponding link targets 57 | # won't be visible in the plain text file anyway. 58 | SKIP_INTERNAL_LINKS = True 59 | 60 | # Use inline, rather than reference, formatting for images and links 61 | INLINE_LINKS = True 62 | 63 | # Number of pixels Google indents nested lists 64 | GOOGLE_LIST_INDENT = 36 65 | 66 | IGNORE_ANCHORS = False 67 | IGNORE_IMAGES = False 68 | IGNORE_EMPHASIS = False 69 | 70 | ### Entity Nonsense ### 71 | 72 | def name2cp(k): 73 | if k == 'apos': return ord("'") 74 | if hasattr(htmlentitydefs, "name2codepoint"): # requires Python 2.3 75 | return htmlentitydefs.name2codepoint[k] 76 | else: 77 | k = htmlentitydefs.entitydefs[k] 78 | if k.startswith("&#") and k.endswith(";"): return int(k[2:-1]) # not in latin-1 79 | return ord(codecs.latin_1_decode(k)[0]) 80 | 81 | unifiable = {'rsquo':"'", 'lsquo':"'", 'rdquo':'"', 'ldquo':'"', 82 | 'copy':'(C)', 'mdash':'--', 'nbsp':' ', 'rarr':'->', 'larr':'<-', 'middot':'*', 83 | 'ndash':'-', 'oelig':'oe', 'aelig':'ae', 84 | 'agrave':'a', 'aacute':'a', 'acirc':'a', 'atilde':'a', 'auml':'a', 'aring':'a', 85 | 'egrave':'e', 'eacute':'e', 'ecirc':'e', 'euml':'e', 86 | 'igrave':'i', 'iacute':'i', 'icirc':'i', 'iuml':'i', 87 | 'ograve':'o', 'oacute':'o', 'ocirc':'o', 'otilde':'o', 'ouml':'o', 88 | 'ugrave':'u', 'uacute':'u', 'ucirc':'u', 'uuml':'u', 89 | 'lrm':'', 'rlm':''} 90 | 91 | unifiable_n = {} 92 | 93 | for k in unifiable.keys(): 94 | unifiable_n[name2cp(k)] = unifiable[k] 95 | 96 | ### End Entity Nonsense ### 97 | 98 | def onlywhite(line): 99 | """Return true if the line does only consist of whitespace characters.""" 100 | for c in line: 101 | if c is not ' ' and c is not ' ': 102 | return c is ' ' 103 | return line 104 | 105 | def hn(tag): 106 | if tag[0] == 'h' and len(tag) == 2: 107 | try: 108 | n = int(tag[1]) 109 | if n in range(1, 10): return n 110 | except ValueError: return 0 111 | 112 | def dumb_property_dict(style): 113 | """returns a hash of css attributes""" 114 | return dict([(x.strip(), y.strip()) for x, y in [z.split(':', 1) for z in style.split(';') if ':' in z]]); 115 | 116 | def dumb_css_parser(data): 117 | """returns a hash of css selectors, each of which contains a hash of css attributes""" 118 | # remove @import sentences 119 | data += ';' 120 | importIndex = data.find('@import') 121 | while importIndex != -1: 122 | data = data[0:importIndex] + data[data.find(';', importIndex) + 1:] 123 | importIndex = data.find('@import') 124 | 125 | # parse the css. reverted from dictionary compehension in order to support older pythons 126 | elements = [x.split('{') for x in data.split('}') if '{' in x.strip()] 127 | try: 128 | elements = dict([(a.strip(), dumb_property_dict(b)) for a, b in elements]) 129 | except ValueError: 130 | elements = {} # not that important 131 | 132 | return elements 133 | 134 | def element_style(attrs, style_def, parent_style): 135 | """returns a hash of the 'final' style attributes of the element""" 136 | style = parent_style.copy() 137 | if 'class' in attrs: 138 | for css_class in attrs['class'].split(): 139 | css_style = style_def['.' + css_class] 140 | style.update(css_style) 141 | if 'style' in attrs: 142 | immediate_style = dumb_property_dict(attrs['style']) 143 | style.update(immediate_style) 144 | return style 145 | 146 | def google_list_style(style): 147 | """finds out whether this is an ordered or unordered list""" 148 | if 'list-style-type' in style: 149 | list_style = style['list-style-type'] 150 | if list_style in ['disc', 'circle', 'square', 'none']: 151 | return 'ul' 152 | return 'ol' 153 | 154 | def google_has_height(style): 155 | """check if the style of the element has the 'height' attribute explicitly defined""" 156 | if 'height' in style: 157 | return True 158 | return False 159 | 160 | def google_text_emphasis(style): 161 | """return a list of all emphasis modifiers of the element""" 162 | emphasis = [] 163 | if 'text-decoration' in style: 164 | emphasis.append(style['text-decoration']) 165 | if 'font-style' in style: 166 | emphasis.append(style['font-style']) 167 | if 'font-weight' in style: 168 | emphasis.append(style['font-weight']) 169 | return emphasis 170 | 171 | def google_fixed_width_font(style): 172 | """check if the css of the current element defines a fixed width font""" 173 | font_family = '' 174 | if 'font-family' in style: 175 | font_family = style['font-family'] 176 | if 'Courier New' == font_family or 'Consolas' == font_family: 177 | return True 178 | return False 179 | 180 | def list_numbering_start(attrs): 181 | """extract numbering from list element attributes""" 182 | if 'start' in attrs: 183 | return int(attrs['start']) - 1 184 | else: 185 | return 0 186 | 187 | class HTML2Text(HTMLParser.HTMLParser): 188 | def __init__(self, out=None, baseurl=''): 189 | HTMLParser.HTMLParser.__init__(self) 190 | 191 | # Config options 192 | self.unicode_snob = UNICODE_SNOB 193 | self.escape_snob = ESCAPE_SNOB 194 | self.links_each_paragraph = LINKS_EACH_PARAGRAPH 195 | self.body_width = BODY_WIDTH 196 | self.skip_internal_links = SKIP_INTERNAL_LINKS 197 | self.inline_links = INLINE_LINKS 198 | self.google_list_indent = GOOGLE_LIST_INDENT 199 | self.ignore_links = IGNORE_ANCHORS 200 | self.ignore_images = IGNORE_IMAGES 201 | self.ignore_emphasis = IGNORE_EMPHASIS 202 | self.google_doc = False 203 | self.ul_item_mark = '*' 204 | self.emphasis_mark = '_' 205 | self.strong_mark = '**' 206 | 207 | if out is None: 208 | self.out = self.outtextf 209 | else: 210 | self.out = out 211 | 212 | self.outtextlist = [] # empty list to store output characters before they are "joined" 213 | 214 | try: 215 | self.outtext = unicode() 216 | except NameError: # Python3 217 | self.outtext = str() 218 | 219 | self.quiet = 0 220 | self.p_p = 0 # number of newline character to print before next output 221 | self.outcount = 0 222 | self.start = 1 223 | self.space = 0 224 | self.a = [] 225 | self.astack = [] 226 | self.maybe_automatic_link = None 227 | self.absolute_url_matcher = re.compile(r'^[a-zA-Z+]+://') 228 | self.acount = 0 229 | self.list = [] 230 | self.blockquote = 0 231 | self.pre = 0 232 | self.startpre = 0 233 | self.code = False 234 | self.br_toggle = '' 235 | self.lastWasNL = 0 236 | self.lastWasList = False 237 | self.style = 0 238 | self.style_def = {} 239 | self.tag_stack = [] 240 | self.emphasis = 0 241 | self.drop_white_space = 0 242 | self.inheader = False 243 | self.abbr_title = None # current abbreviation definition 244 | self.abbr_data = None # last inner HTML (for abbr being defined) 245 | self.abbr_list = {} # stack of abbreviations to write later 246 | self.baseurl = baseurl 247 | 248 | try: del unifiable_n[name2cp('nbsp')] 249 | except KeyError: pass 250 | unifiable['nbsp'] = ' _place_holder;' 251 | 252 | 253 | def feed(self, data): 254 | data = data.replace("", "") 255 | HTMLParser.HTMLParser.feed(self, data) 256 | 257 | def handle(self, data): 258 | self.feed(data) 259 | self.feed("") 260 | return self.optwrap(self.close()) 261 | 262 | def outtextf(self, s): 263 | self.outtextlist.append(s) 264 | if s: self.lastWasNL = s[-1] == '\n' 265 | 266 | def close(self): 267 | HTMLParser.HTMLParser.close(self) 268 | 269 | self.pbr() 270 | self.o('', 0, 'end') 271 | 272 | self.outtext = self.outtext.join(self.outtextlist) 273 | if self.unicode_snob: 274 | try: 275 | nbsp = unichr(name2cp('nbsp')) 276 | except: 277 | nbsp = chr(name2cp('nbsp')) 278 | else: 279 | nbsp = strtype(' ') 280 | self.outtext = self.outtext.replace(strtype(' _place_holder;'), nbsp) 281 | 282 | return self.outtext 283 | 284 | def handle_charref(self, c): 285 | self.o(self.charref(c), 1) 286 | 287 | def handle_entityref(self, c): 288 | self.o(self.entityref(c), 1) 289 | 290 | def handle_starttag(self, tag, attrs): 291 | self.handle_tag(tag, attrs, 1) 292 | 293 | def handle_endtag(self, tag): 294 | self.handle_tag(tag, None, 0) 295 | 296 | def previousIndex(self, attrs): 297 | """ returns the index of certain set of attributes (of a link) in the 298 | self.a list 299 | 300 | If the set of attributes is not found, returns None 301 | """ 302 | if not has_key(attrs, 'href'): return None 303 | 304 | i = -1 305 | for a in self.a: 306 | i += 1 307 | match = 0 308 | 309 | if has_key(a, 'href') and a['href'] == attrs['href']: 310 | if has_key(a, 'title') or has_key(attrs, 'title'): 311 | if (has_key(a, 'title') and has_key(attrs, 'title') and 312 | a['title'] == attrs['title']): 313 | match = True 314 | else: 315 | match = True 316 | 317 | if match: return i 318 | 319 | def drop_last(self, nLetters): 320 | if not self.quiet: 321 | self.outtext = self.outtext[:-nLetters] 322 | 323 | def handle_emphasis(self, start, tag_style, parent_style): 324 | """handles various text emphases""" 325 | tag_emphasis = google_text_emphasis(tag_style) 326 | parent_emphasis = google_text_emphasis(parent_style) 327 | 328 | # handle Google's text emphasis 329 | strikethrough = 'line-through' in tag_emphasis and self.hide_strikethrough 330 | bold = 'bold' in tag_emphasis and not 'bold' in parent_emphasis 331 | italic = 'italic' in tag_emphasis and not 'italic' in parent_emphasis 332 | fixed = google_fixed_width_font(tag_style) and not \ 333 | google_fixed_width_font(parent_style) and not self.pre 334 | 335 | if start: 336 | # crossed-out text must be handled before other attributes 337 | # in order not to output qualifiers unnecessarily 338 | if bold or italic or fixed: 339 | self.emphasis += 1 340 | if strikethrough: 341 | self.quiet += 1 342 | if italic: 343 | self.o(self.emphasis_mark) 344 | self.drop_white_space += 1 345 | if bold: 346 | self.o(self.strong_mark) 347 | self.drop_white_space += 1 348 | if fixed: 349 | self.o('`') 350 | self.drop_white_space += 1 351 | self.code = True 352 | else: 353 | if bold or italic or fixed: 354 | # there must not be whitespace before closing emphasis mark 355 | self.emphasis -= 1 356 | self.space = 0 357 | self.outtext = self.outtext.rstrip() 358 | if fixed: 359 | if self.drop_white_space: 360 | # empty emphasis, drop it 361 | self.drop_last(1) 362 | self.drop_white_space -= 1 363 | else: 364 | self.o('`') 365 | self.code = False 366 | if bold: 367 | if self.drop_white_space: 368 | # empty emphasis, drop it 369 | self.drop_last(2) 370 | self.drop_white_space -= 1 371 | else: 372 | self.o(self.strong_mark) 373 | if italic: 374 | if self.drop_white_space: 375 | # empty emphasis, drop it 376 | self.drop_last(1) 377 | self.drop_white_space -= 1 378 | else: 379 | self.o(self.emphasis_mark) 380 | # space is only allowed after *all* emphasis marks 381 | if (bold or italic) and not self.emphasis: 382 | self.o(" ") 383 | if strikethrough: 384 | self.quiet -= 1 385 | 386 | def handle_tag(self, tag, attrs, start): 387 | #attrs = fixattrs(attrs) 388 | if attrs is None: 389 | attrs = {} 390 | else: 391 | attrs = dict(attrs) 392 | 393 | if self.google_doc: 394 | # the attrs parameter is empty for a closing tag. in addition, we 395 | # need the attributes of the parent nodes in order to get a 396 | # complete style description for the current element. we assume 397 | # that google docs export well formed html. 398 | parent_style = {} 399 | if start: 400 | if self.tag_stack: 401 | parent_style = self.tag_stack[-1][2] 402 | tag_style = element_style(attrs, self.style_def, parent_style) 403 | self.tag_stack.append((tag, attrs, tag_style)) 404 | else: 405 | dummy, attrs, tag_style = self.tag_stack.pop() 406 | if self.tag_stack: 407 | parent_style = self.tag_stack[-1][2] 408 | 409 | if hn(tag): 410 | self.p() 411 | if start: 412 | self.inheader = True 413 | self.o(hn(tag)*"#" + ' ') 414 | else: 415 | self.inheader = False 416 | return # prevent redundant emphasis marks on headers 417 | 418 | if tag in ['p', 'div']: 419 | if self.google_doc: 420 | if start and google_has_height(tag_style): 421 | self.p() 422 | else: 423 | self.soft_br() 424 | else: 425 | self.p() 426 | 427 | if tag == "br" and start: self.o(" \n") 428 | 429 | if tag == "hr" and start: 430 | self.p() 431 | self.o("* * *") 432 | self.p() 433 | 434 | if tag in ["head", "style", 'script']: 435 | if start: self.quiet += 1 436 | else: self.quiet -= 1 437 | 438 | if tag == "style": 439 | if start: self.style += 1 440 | else: self.style -= 1 441 | 442 | if tag in ["body"]: 443 | self.quiet = 0 # sites like 9rules.com never close 444 | 445 | if tag == "blockquote": 446 | if start: 447 | self.p(); self.o('> ', 0, 1); self.start = 1 448 | self.blockquote += 1 449 | else: 450 | self.blockquote -= 1 451 | self.p() 452 | 453 | if tag in ['em', 'i', 'u'] and not self.ignore_emphasis: self.o(self.emphasis_mark) 454 | if tag in ['strong', 'b'] and not self.ignore_emphasis: self.o(self.strong_mark) 455 | if tag in ['del', 'strike', 's']: 456 | if start: 457 | self.o("<"+tag+">") 458 | else: 459 | self.o("") 460 | 461 | if self.google_doc: 462 | if not self.inheader: 463 | # handle some font attributes, but leave headers clean 464 | self.handle_emphasis(start, tag_style, parent_style) 465 | 466 | if tag in ["code", "tt"] and not self.pre: self.o('`') #TODO: `` `this` `` 467 | if tag == "abbr": 468 | if start: 469 | self.abbr_title = None 470 | self.abbr_data = '' 471 | if has_key(attrs, 'title'): 472 | self.abbr_title = attrs['title'] 473 | else: 474 | if self.abbr_title != None: 475 | self.abbr_list[self.abbr_data] = self.abbr_title 476 | self.abbr_title = None 477 | self.abbr_data = '' 478 | 479 | if tag == "a" and not self.ignore_links: 480 | if start: 481 | if has_key(attrs, 'href') and not (self.skip_internal_links and attrs['href'].startswith('#')): 482 | self.astack.append(attrs) 483 | self.maybe_automatic_link = attrs['href'] 484 | else: 485 | self.astack.append(None) 486 | else: 487 | if self.astack: 488 | a = self.astack.pop() 489 | if self.maybe_automatic_link: 490 | self.maybe_automatic_link = None 491 | elif a: 492 | if self.inline_links: 493 | self.o("](" + escape_md(a['href']) + ")") 494 | else: 495 | i = self.previousIndex(a) 496 | if i is not None: 497 | a = self.a[i] 498 | else: 499 | self.acount += 1 500 | a['count'] = self.acount 501 | a['outcount'] = self.outcount 502 | self.a.append(a) 503 | self.o("][" + str(a['count']) + "]") 504 | 505 | if tag == "img" and start and not self.ignore_images: 506 | if has_key(attrs, 'src'): 507 | attrs['href'] = attrs['src'] 508 | alt = attrs.get('alt', '') 509 | self.o("![" + escape_md(alt) + "]") 510 | 511 | if self.inline_links: 512 | self.o("(" + escape_md(attrs['href']) + ")") 513 | else: 514 | i = self.previousIndex(attrs) 515 | if i is not None: 516 | attrs = self.a[i] 517 | else: 518 | self.acount += 1 519 | attrs['count'] = self.acount 520 | attrs['outcount'] = self.outcount 521 | self.a.append(attrs) 522 | self.o("[" + str(attrs['count']) + "]") 523 | 524 | if tag == 'dl' and start: self.p() 525 | if tag == 'dt' and not start: self.pbr() 526 | if tag == 'dd' and start: self.o(' ') 527 | if tag == 'dd' and not start: self.pbr() 528 | 529 | if tag in ["ol", "ul"]: 530 | # Google Docs create sub lists as top level lists 531 | if (not self.list) and (not self.lastWasList): 532 | self.p() 533 | if start: 534 | if self.google_doc: 535 | list_style = google_list_style(tag_style) 536 | else: 537 | list_style = tag 538 | numbering_start = list_numbering_start(attrs) 539 | self.list.append({'name':list_style, 'num':numbering_start}) 540 | else: 541 | if self.list: self.list.pop() 542 | self.lastWasList = True 543 | else: 544 | self.lastWasList = False 545 | 546 | if tag == 'li': 547 | self.pbr() 548 | if start: 549 | if self.list: li = self.list[-1] 550 | else: li = {'name':'ul', 'num':0} 551 | if self.google_doc: 552 | nest_count = self.google_nest_count(tag_style) 553 | else: 554 | nest_count = len(self.list) 555 | self.o(" " * nest_count) #TODO: line up
  1. s > 9 correctly. 556 | if li['name'] == "ul": self.o(self.ul_item_mark + " ") 557 | elif li['name'] == "ol": 558 | li['num'] += 1 559 | self.o(str(li['num'])+". ") 560 | self.start = 1 561 | 562 | if tag in ["table", "tr"] and start: self.p() 563 | if tag == 'td': self.pbr() 564 | 565 | if tag == "pre": 566 | if start: 567 | self.startpre = 1 568 | self.pre = 1 569 | else: 570 | self.pre = 0 571 | self.p() 572 | 573 | def pbr(self): 574 | if self.p_p == 0: 575 | self.p_p = 1 576 | 577 | def p(self): 578 | self.p_p = 2 579 | 580 | def soft_br(self): 581 | self.pbr() 582 | self.br_toggle = ' ' 583 | 584 | def o(self, data, puredata=0, force=0): 585 | if self.abbr_data is not None: 586 | self.abbr_data += data 587 | 588 | if not self.quiet: 589 | if self.google_doc: 590 | # prevent white space immediately after 'begin emphasis' marks ('**' and '_') 591 | lstripped_data = data.lstrip() 592 | if self.drop_white_space and not (self.pre or self.code): 593 | data = lstripped_data 594 | if lstripped_data != '': 595 | self.drop_white_space = 0 596 | 597 | if puredata and not self.pre: 598 | data = re.sub('\s+', ' ', data) 599 | if data and data[0] == ' ': 600 | self.space = 1 601 | data = data[1:] 602 | if not data and not force: return 603 | 604 | if self.startpre: 605 | #self.out(" :") #TODO: not output when already one there 606 | if not data.startswith("\n"): # 
    stuff...
607 |                     data = "\n" + data
608 | 
609 |             bq = (">" * self.blockquote)
610 |             if not (force and data and data[0] == ">") and self.blockquote: bq += " "
611 | 
612 |             if self.pre:
613 |                 if not self.list:
614 |                     bq += "    "
615 |                 #else: list content is already partially indented
616 |                 for i in xrange(len(self.list)):
617 |                     bq += "    "
618 |                 data = data.replace("\n", "\n"+bq)
619 | 
620 |             if self.startpre:
621 |                 self.startpre = 0
622 |                 if self.list:
623 |                     data = data.lstrip("\n") # use existing initial indentation
624 | 
625 |             if self.start:
626 |                 self.space = 0
627 |                 self.p_p = 0
628 |                 self.start = 0
629 | 
630 |             if force == 'end':
631 |                 # It's the end.
632 |                 self.p_p = 0
633 |                 self.out("\n")
634 |                 self.space = 0
635 | 
636 |             if self.p_p:
637 |                 self.out((self.br_toggle+'\n'+bq)*self.p_p)
638 |                 self.space = 0
639 |                 self.br_toggle = ''
640 | 
641 |             if self.space:
642 |                 if not self.lastWasNL: self.out(' ')
643 |                 self.space = 0
644 | 
645 |             if self.a and ((self.p_p == 2 and self.links_each_paragraph) or force == "end"):
646 |                 if force == "end": self.out("\n")
647 | 
648 |                 newa = []
649 |                 for link in self.a:
650 |                     if self.outcount > link['outcount']:
651 |                         self.out("   ["+ str(link['count']) +"]: " + urlparse.urljoin(self.baseurl, link['href']))
652 |                         if has_key(link, 'title'): self.out(" ("+link['title']+")")
653 |                         self.out("\n")
654 |                     else:
655 |                         newa.append(link)
656 | 
657 |                 if self.a != newa: self.out("\n") # Don't need an extra line when nothing was done.
658 | 
659 |                 self.a = newa
660 | 
661 |             if self.abbr_list and force == "end":
662 |                 for abbr, definition in self.abbr_list.items():
663 |                     self.out("  *[" + abbr + "]: " + definition + "\n")
664 | 
665 |             self.p_p = 0
666 |             self.out(data)
667 |             self.outcount += 1
668 | 
669 |     def handle_data(self, data):
670 |         if r'\/script>' in data: self.quiet -= 1
671 | 
672 |         if self.style:
673 |             self.style_def.update(dumb_css_parser(data))
674 | 
675 |         if not self.maybe_automatic_link is None:
676 |             href = self.maybe_automatic_link
677 |             if href == data and self.absolute_url_matcher.match(href):
678 |                 self.o("<" + data + ">")
679 |                 return
680 |             else:
681 |                 self.o("[")
682 |                 self.maybe_automatic_link = None
683 | 
684 |         if not self.code and not self.pre:
685 |             data = escape_md_section(data, snob=self.escape_snob)
686 |         self.o(data, 1)
687 | 
688 |     def unknown_decl(self, data): pass
689 | 
690 |     def charref(self, name):
691 |         if name[0] in ['x','X']:
692 |             c = int(name[1:], 16)
693 |         else:
694 |             c = int(name)
695 | 
696 |         if not self.unicode_snob and c in unifiable_n.keys():
697 |             return unifiable_n[c]
698 |         else:
699 |             try:
700 |                 return unichr(c)
701 |             except NameError: #Python3
702 |                 return chr(c)
703 | 
704 |     def entityref(self, c):
705 |         if not self.unicode_snob and c in unifiable.keys():
706 |             return unifiable[c]
707 |         else:
708 |             try: name2cp(c)
709 |             except KeyError: return "&" + c + ';'
710 |             else:
711 |                 try:
712 |                     return unichr(name2cp(c))
713 |                 except NameError: #Python3
714 |                     return chr(name2cp(c))
715 | 
716 |     def replaceEntities(self, s):
717 |         s = s.group(1)
718 |         if s[0] == "#":
719 |             return self.charref(s[1:])
720 |         else: return self.entityref(s)
721 | 
722 |     r_unescape = re.compile(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));")
723 |     def unescape(self, s):
724 |         return self.r_unescape.sub(self.replaceEntities, s)
725 | 
726 |     def google_nest_count(self, style):
727 |         """calculate the nesting count of google doc lists"""
728 |         nest_count = 0
729 |         if 'margin-left' in style:
730 |             nest_count = int(style['margin-left'][:-2]) / self.google_list_indent
731 |         return nest_count
732 | 
733 | 
734 |     def optwrap(self, text):
735 |         """Wrap all paragraphs in the provided text."""
736 |         if not self.body_width:
737 |             return text
738 | 
739 |         assert wrap, "Requires Python 2.3."
740 |         result = ''
741 |         newlines = 0
742 |         for para in text.split("\n"):
743 |             if len(para) > 0:
744 |                 if not skipwrap(para):
745 |                     result += "\n".join(wrap(para, self.body_width))
746 |                     if para.endswith('  '):
747 |                         result += "  \n"
748 |                         newlines = 1
749 |                     else:
750 |                         result += "\n\n"
751 |                         newlines = 2
752 |                 else:
753 |                     if not onlywhite(para):
754 |                         result += para + "\n"
755 |                         newlines = 1
756 |             else:
757 |                 if newlines < 2:
758 |                     result += "\n"
759 |                     newlines += 1
760 |         return result
761 | 
762 | ordered_list_matcher = re.compile(r'\d+\.\s')
763 | unordered_list_matcher = re.compile(r'[-\*\+]\s')
764 | md_chars_matcher = re.compile(r"([\\\[\]\(\)])")
765 | md_chars_matcher_all = re.compile(r"([`\*_{}\[\]\(\)#!])")
766 | md_dot_matcher = re.compile(r"""
767 |     ^             # start of line
768 |     (\s*\d+)      # optional whitespace and a number
769 |     (\.)          # dot
770 |     (?=\s)        # lookahead assert whitespace
771 |     """, re.MULTILINE | re.VERBOSE)
772 | md_plus_matcher = re.compile(r"""
773 |     ^
774 |     (\s*)
775 |     (\+)
776 |     (?=\s)
777 |     """, flags=re.MULTILINE | re.VERBOSE)
778 | md_dash_matcher = re.compile(r"""
779 |     ^
780 |     (\s*)
781 |     (-)
782 |     (?=\s|\-)     # followed by whitespace (bullet list, or spaced out hr)
783 |                   # or another dash (header or hr)
784 |     """, flags=re.MULTILINE | re.VERBOSE)
785 | slash_chars = r'\`*_{}[]()#+-.!'
786 | md_backslash_matcher = re.compile(r'''
787 |     (\\)          # match one slash
788 |     (?=[%s])      # followed by a char that requires escaping
789 |     ''' % re.escape(slash_chars),
790 |     flags=re.VERBOSE)
791 | 
792 | def skipwrap(para):
793 |     # If the text begins with four spaces or one tab, it's a code block; don't wrap
794 |     if para[0:4] == '    ' or para[0] == '\t':
795 |         return True
796 |     # If the text begins with only two "--", possibly preceded by whitespace, that's
797 |     # an emdash; so wrap.
798 |     stripped = para.lstrip()
799 |     if stripped[0:2] == "--" and len(stripped) > 2 and stripped[2] != "-":
800 |         return False
801 |     # I'm not sure what this is for; I thought it was to detect lists, but there's
802 |     # a 
    -inside- case in one of the tests that also depends upon it.
803 |     if stripped[0:1] == '-' or stripped[0:1] == '*':
804 |         return True
805 |     # If the text begins with a single -, *, or +, followed by a space, or an integer,
806 |     # followed by a ., followed by a space (in either case optionally preceeded by
807 |     # whitespace), it's a list; don't wrap.
808 |     if ordered_list_matcher.match(stripped) or unordered_list_matcher.match(stripped):
809 |         return True
810 |     return False
811 | 
812 | def wrapwrite(text):
813 |     text = text.encode('utf-8')
814 |     try: #Python3
815 |         sys.stdout.buffer.write(text)
816 |     except AttributeError:
817 |         sys.stdout.write(text)
818 | 
819 | def html2text(html, baseurl=''):
820 |     h = HTML2Text(baseurl=baseurl)
821 |     return h.handle(html)
822 | 
823 | def unescape(s, unicode_snob=False):
824 |     h = HTML2Text()
825 |     h.unicode_snob = unicode_snob
826 |     return h.unescape(s)
827 | 
828 | def escape_md(text):
829 |     """Escapes markdown-sensitive characters within other markdown constructs."""
830 |     return md_chars_matcher.sub(r"\\\1", text)
831 | 
832 | def escape_md_section(text, snob=False):
833 |     """Escapes markdown-sensitive characters across whole document sections."""
834 |     text = md_backslash_matcher.sub(r"\\\1", text)
835 |     if snob:
836 |         text = md_chars_matcher_all.sub(r"\\\1", text)
837 |     text = md_dot_matcher.sub(r"\1\\\2", text)
838 |     text = md_plus_matcher.sub(r"\1\\\2", text)
839 |     text = md_dash_matcher.sub(r"\1\\\2", text)
840 |     return text
841 | 
842 | 
843 | def main():
844 |     baseurl = ''
845 | 
846 |     p = optparse.OptionParser('%prog [(filename|url) [encoding]]',
847 |                               version='%prog ' + __version__)
848 |     p.add_option("--ignore-emphasis", dest="ignore_emphasis", action="store_true",
849 |         default=IGNORE_EMPHASIS, help="don't include any formatting for emphasis")
850 |     p.add_option("--ignore-links", dest="ignore_links", action="store_true",
851 |         default=IGNORE_ANCHORS, help="don't include any formatting for links")
852 |     p.add_option("--ignore-images", dest="ignore_images", action="store_true",
853 |         default=IGNORE_IMAGES, help="don't include any formatting for images")
854 |     p.add_option("-g", "--google-doc", action="store_true", dest="google_doc",
855 |         default=False, help="convert an html-exported Google Document")
856 |     p.add_option("-d", "--dash-unordered-list", action="store_true", dest="ul_style_dash",
857 |         default=False, help="use a dash rather than a star for unordered list items")
858 |     p.add_option("-e", "--asterisk-emphasis", action="store_true", dest="em_style_asterisk",
859 |         default=False, help="use an asterisk rather than an underscore for emphasized text")
860 |     p.add_option("-b", "--body-width", dest="body_width", action="store", type="int",
861 |         default=BODY_WIDTH, help="number of characters per output line, 0 for no wrap")
862 |     p.add_option("-i", "--google-list-indent", dest="list_indent", action="store", type="int",
863 |         default=GOOGLE_LIST_INDENT, help="number of pixels Google indents nested lists")
864 |     p.add_option("-s", "--hide-strikethrough", action="store_true", dest="hide_strikethrough",
865 |         default=False, help="hide strike-through text. only relevant when -g is specified as well")
866 |     p.add_option("--escape-all", action="store_true", dest="escape_snob",
867 |         default=False, help="Escape all special characters.  Output is less readable, but avoids corner case formatting issues.")
868 |     (options, args) = p.parse_args()
869 | 
870 |     # process input
871 |     encoding = "utf-8"
872 |     if len(args) > 0:
873 |         file_ = args[0]
874 |         if len(args) == 2:
875 |             encoding = args[1]
876 |         if len(args) > 2:
877 |             p.error('Too many arguments')
878 | 
879 |         if file_.startswith('http://') or file_.startswith('https://'):
880 |             baseurl = file_
881 |             j = urllib.urlopen(baseurl)
882 |             data = j.read()
883 |             if encoding is None:
884 |                 try:
885 |                     from feedparser import _getCharacterEncoding as enc
886 |                 except ImportError:
887 |                     enc = lambda x, y: ('utf-8', 1)
888 |                 encoding = enc(j.headers, data)[0]
889 |                 if encoding == 'us-ascii':
890 |                     encoding = 'utf-8'
891 |         else:
892 |             data = open(file_, 'rb').read()
893 |             if encoding is None:
894 |                 try:
895 |                     from chardet import detect
896 |                 except ImportError:
897 |                     detect = lambda x: {'encoding': 'utf-8'}
898 |                 encoding = detect(data)['encoding']
899 |     else:
900 |         data = sys.stdin.read()
901 | 
902 |     if PY2:
903 |         data = data.decode(encoding)
904 | 
905 |     h = HTML2Text(baseurl=baseurl)
906 |     # handle options
907 |     if options.ul_style_dash: h.ul_item_mark = '-'
908 |     if options.em_style_asterisk:
909 |         h.emphasis_mark = '*'
910 |         h.strong_mark = '__'
911 | 
912 |     h.body_width = options.body_width
913 |     h.list_indent = options.list_indent
914 |     h.ignore_emphasis = options.ignore_emphasis
915 |     h.ignore_links = options.ignore_links
916 |     h.ignore_images = options.ignore_images
917 |     h.google_doc = options.google_doc
918 |     h.hide_strikethrough = options.hide_strikethrough
919 |     h.escape_snob = options.escape_snob
920 | 
921 |     wrapwrite(h.handle(data))
922 | 
923 | 
924 | if __name__ == "__main__":
925 |     main()
926 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 |                     GNU GENERAL PUBLIC LICENSE
  2 |                        Version 3, 29 June 2007
  3 | 
  4 |  Copyright (C) 2007 Free Software Foundation, Inc. 
  5 |  Everyone is permitted to copy and distribute verbatim copies
  6 |  of this license document, but changing it is not allowed.
  7 | 
  8 |                             Preamble
  9 | 
 10 |   The GNU General Public License is a free, copyleft license for
 11 | software and other kinds of works.
 12 | 
 13 |   The licenses for most software and other practical works are designed
 14 | to take away your freedom to share and change the works.  By contrast,
 15 | the GNU General Public License is intended to guarantee your freedom to
 16 | share and change all versions of a program--to make sure it remains free
 17 | software for all its users.  We, the Free Software Foundation, use the
 18 | GNU General Public License for most of our software; it applies also to
 19 | any other work released this way by its authors.  You can apply it to
 20 | your programs, too.
 21 | 
 22 |   When we speak of free software, we are referring to freedom, not
 23 | price.  Our General Public Licenses are designed to make sure that you
 24 | have the freedom to distribute copies of free software (and charge for
 25 | them if you wish), that you receive source code or can get it if you
 26 | want it, that you can change the software or use pieces of it in new
 27 | free programs, and that you know you can do these things.
 28 | 
 29 |   To protect your rights, we need to prevent others from denying you
 30 | these rights or asking you to surrender the rights.  Therefore, you have
 31 | certain responsibilities if you distribute copies of the software, or if
 32 | you modify it: responsibilities to respect the freedom of others.
 33 | 
 34 |   For example, if you distribute copies of such a program, whether
 35 | gratis or for a fee, you must pass on to the recipients the same
 36 | freedoms that you received.  You must make sure that they, too, receive
 37 | or can get the source code.  And you must show them these terms so they
 38 | know their rights.
 39 | 
 40 |   Developers that use the GNU GPL protect your rights with two steps:
 41 | (1) assert copyright on the software, and (2) offer you this License
 42 | giving you legal permission to copy, distribute and/or modify it.
 43 | 
 44 |   For the developers' and authors' protection, the GPL clearly explains
 45 | that there is no warranty for this free software.  For both users' and
 46 | authors' sake, the GPL requires that modified versions be marked as
 47 | changed, so that their problems will not be attributed erroneously to
 48 | authors of previous versions.
 49 | 
 50 |   Some devices are designed to deny users access to install or run
 51 | modified versions of the software inside them, although the manufacturer
 52 | can do so.  This is fundamentally incompatible with the aim of
 53 | protecting users' freedom to change the software.  The systematic
 54 | pattern of such abuse occurs in the area of products for individuals to
 55 | use, which is precisely where it is most unacceptable.  Therefore, we
 56 | have designed this version of the GPL to prohibit the practice for those
 57 | products.  If such problems arise substantially in other domains, we
 58 | stand ready to extend this provision to those domains in future versions
 59 | of the GPL, as needed to protect the freedom of users.
 60 | 
 61 |   Finally, every program is threatened constantly by software patents.
 62 | States should not allow patents to restrict development and use of
 63 | software on general-purpose computers, but in those that do, we wish to
 64 | avoid the special danger that patents applied to a free program could
 65 | make it effectively proprietary.  To prevent this, the GPL assures that
 66 | patents cannot be used to render the program non-free.
 67 | 
 68 |   The precise terms and conditions for copying, distribution and
 69 | modification follow.
 70 | 
 71 |                        TERMS AND CONDITIONS
 72 | 
 73 |   0. Definitions.
 74 | 
 75 |   "This License" refers to version 3 of the GNU General Public License.
 76 | 
 77 |   "Copyright" also means copyright-like laws that apply to other kinds of
 78 | works, such as semiconductor masks.
 79 | 
 80 |   "The Program" refers to any copyrightable work licensed under this
 81 | License.  Each licensee is addressed as "you".  "Licensees" and
 82 | "recipients" may be individuals or organizations.
 83 | 
 84 |   To "modify" a work means to copy from or adapt all or part of the work
 85 | in a fashion requiring copyright permission, other than the making of an
 86 | exact copy.  The resulting work is called a "modified version" of the
 87 | earlier work or a work "based on" the earlier work.
 88 | 
 89 |   A "covered work" means either the unmodified Program or a work based
 90 | on the Program.
 91 | 
 92 |   To "propagate" a work means to do anything with it that, without
 93 | permission, would make you directly or secondarily liable for
 94 | infringement under applicable copyright law, except executing it on a
 95 | computer or modifying a private copy.  Propagation includes copying,
 96 | distribution (with or without modification), making available to the
 97 | public, and in some countries other activities as well.
 98 | 
 99 |   To "convey" a work means any kind of propagation that enables other
100 | parties to make or receive copies.  Mere interaction with a user through
101 | a computer network, with no transfer of a copy, is not conveying.
102 | 
103 |   An interactive user interface displays "Appropriate Legal Notices"
104 | to the extent that it includes a convenient and prominently visible
105 | feature that (1) displays an appropriate copyright notice, and (2)
106 | tells the user that there is no warranty for the work (except to the
107 | extent that warranties are provided), that licensees may convey the
108 | work under this License, and how to view a copy of this License.  If
109 | the interface presents a list of user commands or options, such as a
110 | menu, a prominent item in the list meets this criterion.
111 | 
112 |   1. Source Code.
113 | 
114 |   The "source code" for a work means the preferred form of the work
115 | for making modifications to it.  "Object code" means any non-source
116 | form of a work.
117 | 
118 |   A "Standard Interface" means an interface that either is an official
119 | standard defined by a recognized standards body, or, in the case of
120 | interfaces specified for a particular programming language, one that
121 | is widely used among developers working in that language.
122 | 
123 |   The "System Libraries" of an executable work include anything, other
124 | than the work as a whole, that (a) is included in the normal form of
125 | packaging a Major Component, but which is not part of that Major
126 | Component, and (b) serves only to enable use of the work with that
127 | Major Component, or to implement a Standard Interface for which an
128 | implementation is available to the public in source code form.  A
129 | "Major Component", in this context, means a major essential component
130 | (kernel, window system, and so on) of the specific operating system
131 | (if any) on which the executable work runs, or a compiler used to
132 | produce the work, or an object code interpreter used to run it.
133 | 
134 |   The "Corresponding Source" for a work in object code form means all
135 | the source code needed to generate, install, and (for an executable
136 | work) run the object code and to modify the work, including scripts to
137 | control those activities.  However, it does not include the work's
138 | System Libraries, or general-purpose tools or generally available free
139 | programs which are used unmodified in performing those activities but
140 | which are not part of the work.  For example, Corresponding Source
141 | includes interface definition files associated with source files for
142 | the work, and the source code for shared libraries and dynamically
143 | linked subprograms that the work is specifically designed to require,
144 | such as by intimate data communication or control flow between those
145 | subprograms and other parts of the work.
146 | 
147 |   The Corresponding Source need not include anything that users
148 | can regenerate automatically from other parts of the Corresponding
149 | Source.
150 | 
151 |   The Corresponding Source for a work in source code form is that
152 | same work.
153 | 
154 |   2. Basic Permissions.
155 | 
156 |   All rights granted under this License are granted for the term of
157 | copyright on the Program, and are irrevocable provided the stated
158 | conditions are met.  This License explicitly affirms your unlimited
159 | permission to run the unmodified Program.  The output from running a
160 | covered work is covered by this License only if the output, given its
161 | content, constitutes a covered work.  This License acknowledges your
162 | rights of fair use or other equivalent, as provided by copyright law.
163 | 
164 |   You may make, run and propagate covered works that you do not
165 | convey, without conditions so long as your license otherwise remains
166 | in force.  You may convey covered works to others for the sole purpose
167 | of having them make modifications exclusively for you, or provide you
168 | with facilities for running those works, provided that you comply with
169 | the terms of this License in conveying all material for which you do
170 | not control copyright.  Those thus making or running the covered works
171 | for you must do so exclusively on your behalf, under your direction
172 | and control, on terms that prohibit them from making any copies of
173 | your copyrighted material outside their relationship with you.
174 | 
175 |   Conveying under any other circumstances is permitted solely under
176 | the conditions stated below.  Sublicensing is not allowed; section 10
177 | makes it unnecessary.
178 | 
179 |   3. Protecting Users' Legal Rights From Anti-Circumvention Law.
180 | 
181 |   No covered work shall be deemed part of an effective technological
182 | measure under any applicable law fulfilling obligations under article
183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or
184 | similar laws prohibiting or restricting circumvention of such
185 | measures.
186 | 
187 |   When you convey a covered work, you waive any legal power to forbid
188 | circumvention of technological measures to the extent such circumvention
189 | is effected by exercising rights under this License with respect to
190 | the covered work, and you disclaim any intention to limit operation or
191 | modification of the work as a means of enforcing, against the work's
192 | users, your or third parties' legal rights to forbid circumvention of
193 | technological measures.
194 | 
195 |   4. Conveying Verbatim Copies.
196 | 
197 |   You may convey verbatim copies of the Program's source code as you
198 | receive it, in any medium, provided that you conspicuously and
199 | appropriately publish on each copy an appropriate copyright notice;
200 | keep intact all notices stating that this License and any
201 | non-permissive terms added in accord with section 7 apply to the code;
202 | keep intact all notices of the absence of any warranty; and give all
203 | recipients a copy of this License along with the Program.
204 | 
205 |   You may charge any price or no price for each copy that you convey,
206 | and you may offer support or warranty protection for a fee.
207 | 
208 |   5. Conveying Modified Source Versions.
209 | 
210 |   You may convey a work based on the Program, or the modifications to
211 | produce it from the Program, in the form of source code under the
212 | terms of section 4, provided that you also meet all of these conditions:
213 | 
214 |     a) The work must carry prominent notices stating that you modified
215 |     it, and giving a relevant date.
216 | 
217 |     b) The work must carry prominent notices stating that it is
218 |     released under this License and any conditions added under section
219 |     7.  This requirement modifies the requirement in section 4 to
220 |     "keep intact all notices".
221 | 
222 |     c) You must license the entire work, as a whole, under this
223 |     License to anyone who comes into possession of a copy.  This
224 |     License will therefore apply, along with any applicable section 7
225 |     additional terms, to the whole of the work, and all its parts,
226 |     regardless of how they are packaged.  This License gives no
227 |     permission to license the work in any other way, but it does not
228 |     invalidate such permission if you have separately received it.
229 | 
230 |     d) If the work has interactive user interfaces, each must display
231 |     Appropriate Legal Notices; however, if the Program has interactive
232 |     interfaces that do not display Appropriate Legal Notices, your
233 |     work need not make them do so.
234 | 
235 |   A compilation of a covered work with other separate and independent
236 | works, which are not by their nature extensions of the covered work,
237 | and which are not combined with it such as to form a larger program,
238 | in or on a volume of a storage or distribution medium, is called an
239 | "aggregate" if the compilation and its resulting copyright are not
240 | used to limit the access or legal rights of the compilation's users
241 | beyond what the individual works permit.  Inclusion of a covered work
242 | in an aggregate does not cause this License to apply to the other
243 | parts of the aggregate.
244 | 
245 |   6. Conveying Non-Source Forms.
246 | 
247 |   You may convey a covered work in object code form under the terms
248 | of sections 4 and 5, provided that you also convey the
249 | machine-readable Corresponding Source under the terms of this License,
250 | in one of these ways:
251 | 
252 |     a) Convey the object code in, or embodied in, a physical product
253 |     (including a physical distribution medium), accompanied by the
254 |     Corresponding Source fixed on a durable physical medium
255 |     customarily used for software interchange.
256 | 
257 |     b) Convey the object code in, or embodied in, a physical product
258 |     (including a physical distribution medium), accompanied by a
259 |     written offer, valid for at least three years and valid for as
260 |     long as you offer spare parts or customer support for that product
261 |     model, to give anyone who possesses the object code either (1) a
262 |     copy of the Corresponding Source for all the software in the
263 |     product that is covered by this License, on a durable physical
264 |     medium customarily used for software interchange, for a price no
265 |     more than your reasonable cost of physically performing this
266 |     conveying of source, or (2) access to copy the
267 |     Corresponding Source from a network server at no charge.
268 | 
269 |     c) Convey individual copies of the object code with a copy of the
270 |     written offer to provide the Corresponding Source.  This
271 |     alternative is allowed only occasionally and noncommercially, and
272 |     only if you received the object code with such an offer, in accord
273 |     with subsection 6b.
274 | 
275 |     d) Convey the object code by offering access from a designated
276 |     place (gratis or for a charge), and offer equivalent access to the
277 |     Corresponding Source in the same way through the same place at no
278 |     further charge.  You need not require recipients to copy the
279 |     Corresponding Source along with the object code.  If the place to
280 |     copy the object code is a network server, the Corresponding Source
281 |     may be on a different server (operated by you or a third party)
282 |     that supports equivalent copying facilities, provided you maintain
283 |     clear directions next to the object code saying where to find the
284 |     Corresponding Source.  Regardless of what server hosts the
285 |     Corresponding Source, you remain obligated to ensure that it is
286 |     available for as long as needed to satisfy these requirements.
287 | 
288 |     e) Convey the object code using peer-to-peer transmission, provided
289 |     you inform other peers where the object code and Corresponding
290 |     Source of the work are being offered to the general public at no
291 |     charge under subsection 6d.
292 | 
293 |   A separable portion of the object code, whose source code is excluded
294 | from the Corresponding Source as a System Library, need not be
295 | included in conveying the object code work.
296 | 
297 |   A "User Product" is either (1) a "consumer product", which means any
298 | tangible personal property which is normally used for personal, family,
299 | or household purposes, or (2) anything designed or sold for incorporation
300 | into a dwelling.  In determining whether a product is a consumer product,
301 | doubtful cases shall be resolved in favor of coverage.  For a particular
302 | product received by a particular user, "normally used" refers to a
303 | typical or common use of that class of product, regardless of the status
304 | of the particular user or of the way in which the particular user
305 | actually uses, or expects or is expected to use, the product.  A product
306 | is a consumer product regardless of whether the product has substantial
307 | commercial, industrial or non-consumer uses, unless such uses represent
308 | the only significant mode of use of the product.
309 | 
310 |   "Installation Information" for a User Product means any methods,
311 | procedures, authorization keys, or other information required to install
312 | and execute modified versions of a covered work in that User Product from
313 | a modified version of its Corresponding Source.  The information must
314 | suffice to ensure that the continued functioning of the modified object
315 | code is in no case prevented or interfered with solely because
316 | modification has been made.
317 | 
318 |   If you convey an object code work under this section in, or with, or
319 | specifically for use in, a User Product, and the conveying occurs as
320 | part of a transaction in which the right of possession and use of the
321 | User Product is transferred to the recipient in perpetuity or for a
322 | fixed term (regardless of how the transaction is characterized), the
323 | Corresponding Source conveyed under this section must be accompanied
324 | by the Installation Information.  But this requirement does not apply
325 | if neither you nor any third party retains the ability to install
326 | modified object code on the User Product (for example, the work has
327 | been installed in ROM).
328 | 
329 |   The requirement to provide Installation Information does not include a
330 | requirement to continue to provide support service, warranty, or updates
331 | for a work that has been modified or installed by the recipient, or for
332 | the User Product in which it has been modified or installed.  Access to a
333 | network may be denied when the modification itself materially and
334 | adversely affects the operation of the network or violates the rules and
335 | protocols for communication across the network.
336 | 
337 |   Corresponding Source conveyed, and Installation Information provided,
338 | in accord with this section must be in a format that is publicly
339 | documented (and with an implementation available to the public in
340 | source code form), and must require no special password or key for
341 | unpacking, reading or copying.
342 | 
343 |   7. Additional Terms.
344 | 
345 |   "Additional permissions" are terms that supplement the terms of this
346 | License by making exceptions from one or more of its conditions.
347 | Additional permissions that are applicable to the entire Program shall
348 | be treated as though they were included in this License, to the extent
349 | that they are valid under applicable law.  If additional permissions
350 | apply only to part of the Program, that part may be used separately
351 | under those permissions, but the entire Program remains governed by
352 | this License without regard to the additional permissions.
353 | 
354 |   When you convey a copy of a covered work, you may at your option
355 | remove any additional permissions from that copy, or from any part of
356 | it.  (Additional permissions may be written to require their own
357 | removal in certain cases when you modify the work.)  You may place
358 | additional permissions on material, added by you to a covered work,
359 | for which you have or can give appropriate copyright permission.
360 | 
361 |   Notwithstanding any other provision of this License, for material you
362 | add to a covered work, you may (if authorized by the copyright holders of
363 | that material) supplement the terms of this License with terms:
364 | 
365 |     a) Disclaiming warranty or limiting liability differently from the
366 |     terms of sections 15 and 16 of this License; or
367 | 
368 |     b) Requiring preservation of specified reasonable legal notices or
369 |     author attributions in that material or in the Appropriate Legal
370 |     Notices displayed by works containing it; or
371 | 
372 |     c) Prohibiting misrepresentation of the origin of that material, or
373 |     requiring that modified versions of such material be marked in
374 |     reasonable ways as different from the original version; or
375 | 
376 |     d) Limiting the use for publicity purposes of names of licensors or
377 |     authors of the material; or
378 | 
379 |     e) Declining to grant rights under trademark law for use of some
380 |     trade names, trademarks, or service marks; or
381 | 
382 |     f) Requiring indemnification of licensors and authors of that
383 |     material by anyone who conveys the material (or modified versions of
384 |     it) with contractual assumptions of liability to the recipient, for
385 |     any liability that these contractual assumptions directly impose on
386 |     those licensors and authors.
387 | 
388 |   All other non-permissive additional terms are considered "further
389 | restrictions" within the meaning of section 10.  If the Program as you
390 | received it, or any part of it, contains a notice stating that it is
391 | governed by this License along with a term that is a further
392 | restriction, you may remove that term.  If a license document contains
393 | a further restriction but permits relicensing or conveying under this
394 | License, you may add to a covered work material governed by the terms
395 | of that license document, provided that the further restriction does
396 | not survive such relicensing or conveying.
397 | 
398 |   If you add terms to a covered work in accord with this section, you
399 | must place, in the relevant source files, a statement of the
400 | additional terms that apply to those files, or a notice indicating
401 | where to find the applicable terms.
402 | 
403 |   Additional terms, permissive or non-permissive, may be stated in the
404 | form of a separately written license, or stated as exceptions;
405 | the above requirements apply either way.
406 | 
407 |   8. Termination.
408 | 
409 |   You may not propagate or modify a covered work except as expressly
410 | provided under this License.  Any attempt otherwise to propagate or
411 | modify it is void, and will automatically terminate your rights under
412 | this License (including any patent licenses granted under the third
413 | paragraph of section 11).
414 | 
415 |   However, if you cease all violation of this License, then your
416 | license from a particular copyright holder is reinstated (a)
417 | provisionally, unless and until the copyright holder explicitly and
418 | finally terminates your license, and (b) permanently, if the copyright
419 | holder fails to notify you of the violation by some reasonable means
420 | prior to 60 days after the cessation.
421 | 
422 |   Moreover, your license from a particular copyright holder is
423 | reinstated permanently if the copyright holder notifies you of the
424 | violation by some reasonable means, this is the first time you have
425 | received notice of violation of this License (for any work) from that
426 | copyright holder, and you cure the violation prior to 30 days after
427 | your receipt of the notice.
428 | 
429 |   Termination of your rights under this section does not terminate the
430 | licenses of parties who have received copies or rights from you under
431 | this License.  If your rights have been terminated and not permanently
432 | reinstated, you do not qualify to receive new licenses for the same
433 | material under section 10.
434 | 
435 |   9. Acceptance Not Required for Having Copies.
436 | 
437 |   You are not required to accept this License in order to receive or
438 | run a copy of the Program.  Ancillary propagation of a covered work
439 | occurring solely as a consequence of using peer-to-peer transmission
440 | to receive a copy likewise does not require acceptance.  However,
441 | nothing other than this License grants you permission to propagate or
442 | modify any covered work.  These actions infringe copyright if you do
443 | not accept this License.  Therefore, by modifying or propagating a
444 | covered work, you indicate your acceptance of this License to do so.
445 | 
446 |   10. Automatic Licensing of Downstream Recipients.
447 | 
448 |   Each time you convey a covered work, the recipient automatically
449 | receives a license from the original licensors, to run, modify and
450 | propagate that work, subject to this License.  You are not responsible
451 | for enforcing compliance by third parties with this License.
452 | 
453 |   An "entity transaction" is a transaction transferring control of an
454 | organization, or substantially all assets of one, or subdividing an
455 | organization, or merging organizations.  If propagation of a covered
456 | work results from an entity transaction, each party to that
457 | transaction who receives a copy of the work also receives whatever
458 | licenses to the work the party's predecessor in interest had or could
459 | give under the previous paragraph, plus a right to possession of the
460 | Corresponding Source of the work from the predecessor in interest, if
461 | the predecessor has it or can get it with reasonable efforts.
462 | 
463 |   You may not impose any further restrictions on the exercise of the
464 | rights granted or affirmed under this License.  For example, you may
465 | not impose a license fee, royalty, or other charge for exercise of
466 | rights granted under this License, and you may not initiate litigation
467 | (including a cross-claim or counterclaim in a lawsuit) alleging that
468 | any patent claim is infringed by making, using, selling, offering for
469 | sale, or importing the Program or any portion of it.
470 | 
471 |   11. Patents.
472 | 
473 |   A "contributor" is a copyright holder who authorizes use under this
474 | License of the Program or a work on which the Program is based.  The
475 | work thus licensed is called the contributor's "contributor version".
476 | 
477 |   A contributor's "essential patent claims" are all patent claims
478 | owned or controlled by the contributor, whether already acquired or
479 | hereafter acquired, that would be infringed by some manner, permitted
480 | by this License, of making, using, or selling its contributor version,
481 | but do not include claims that would be infringed only as a
482 | consequence of further modification of the contributor version.  For
483 | purposes of this definition, "control" includes the right to grant
484 | patent sublicenses in a manner consistent with the requirements of
485 | this License.
486 | 
487 |   Each contributor grants you a non-exclusive, worldwide, royalty-free
488 | patent license under the contributor's essential patent claims, to
489 | make, use, sell, offer for sale, import and otherwise run, modify and
490 | propagate the contents of its contributor version.
491 | 
492 |   In the following three paragraphs, a "patent license" is any express
493 | agreement or commitment, however denominated, not to enforce a patent
494 | (such as an express permission to practice a patent or covenant not to
495 | sue for patent infringement).  To "grant" such a patent license to a
496 | party means to make such an agreement or commitment not to enforce a
497 | patent against the party.
498 | 
499 |   If you convey a covered work, knowingly relying on a patent license,
500 | and the Corresponding Source of the work is not available for anyone
501 | to copy, free of charge and under the terms of this License, through a
502 | publicly available network server or other readily accessible means,
503 | then you must either (1) cause the Corresponding Source to be so
504 | available, or (2) arrange to deprive yourself of the benefit of the
505 | patent license for this particular work, or (3) arrange, in a manner
506 | consistent with the requirements of this License, to extend the patent
507 | license to downstream recipients.  "Knowingly relying" means you have
508 | actual knowledge that, but for the patent license, your conveying the
509 | covered work in a country, or your recipient's use of the covered work
510 | in a country, would infringe one or more identifiable patents in that
511 | country that you have reason to believe are valid.
512 | 
513 |   If, pursuant to or in connection with a single transaction or
514 | arrangement, you convey, or propagate by procuring conveyance of, a
515 | covered work, and grant a patent license to some of the parties
516 | receiving the covered work authorizing them to use, propagate, modify
517 | or convey a specific copy of the covered work, then the patent license
518 | you grant is automatically extended to all recipients of the covered
519 | work and works based on it.
520 | 
521 |   A patent license is "discriminatory" if it does not include within
522 | the scope of its coverage, prohibits the exercise of, or is
523 | conditioned on the non-exercise of one or more of the rights that are
524 | specifically granted under this License.  You may not convey a covered
525 | work if you are a party to an arrangement with a third party that is
526 | in the business of distributing software, under which you make payment
527 | to the third party based on the extent of your activity of conveying
528 | the work, and under which the third party grants, to any of the
529 | parties who would receive the covered work from you, a discriminatory
530 | patent license (a) in connection with copies of the covered work
531 | conveyed by you (or copies made from those copies), or (b) primarily
532 | for and in connection with specific products or compilations that
533 | contain the covered work, unless you entered into that arrangement,
534 | or that patent license was granted, prior to 28 March 2007.
535 | 
536 |   Nothing in this License shall be construed as excluding or limiting
537 | any implied license or other defenses to infringement that may
538 | otherwise be available to you under applicable patent law.
539 | 
540 |   12. No Surrender of Others' Freedom.
541 | 
542 |   If conditions are imposed on you (whether by court order, agreement or
543 | otherwise) that contradict the conditions of this License, they do not
544 | excuse you from the conditions of this License.  If you cannot convey a
545 | covered work so as to satisfy simultaneously your obligations under this
546 | License and any other pertinent obligations, then as a consequence you may
547 | not convey it at all.  For example, if you agree to terms that obligate you
548 | to collect a royalty for further conveying from those to whom you convey
549 | the Program, the only way you could satisfy both those terms and this
550 | License would be to refrain entirely from conveying the Program.
551 | 
552 |   13. Use with the GNU Affero General Public License.
553 | 
554 |   Notwithstanding any other provision of this License, you have
555 | permission to link or combine any covered work with a work licensed
556 | under version 3 of the GNU Affero General Public License into a single
557 | combined work, and to convey the resulting work.  The terms of this
558 | License will continue to apply to the part which is the covered work,
559 | but the special requirements of the GNU Affero General Public License,
560 | section 13, concerning interaction through a network will apply to the
561 | combination as such.
562 | 
563 |   14. Revised Versions of this License.
564 | 
565 |   The Free Software Foundation may publish revised and/or new versions of
566 | the GNU General Public License from time to time.  Such new versions will
567 | be similar in spirit to the present version, but may differ in detail to
568 | address new problems or concerns.
569 | 
570 |   Each version is given a distinguishing version number.  If the
571 | Program specifies that a certain numbered version of the GNU General
572 | Public License "or any later version" applies to it, you have the
573 | option of following the terms and conditions either of that numbered
574 | version or of any later version published by the Free Software
575 | Foundation.  If the Program does not specify a version number of the
576 | GNU General Public License, you may choose any version ever published
577 | by the Free Software Foundation.
578 | 
579 |   If the Program specifies that a proxy can decide which future
580 | versions of the GNU General Public License can be used, that proxy's
581 | public statement of acceptance of a version permanently authorizes you
582 | to choose that version for the Program.
583 | 
584 |   Later license versions may give you additional or different
585 | permissions.  However, no additional obligations are imposed on any
586 | author or copyright holder as a result of your choosing to follow a
587 | later version.
588 | 
589 |   15. Disclaimer of Warranty.
590 | 
591 |   THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
592 | APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
596 | PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
597 | IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
599 | 
600 |   16. Limitation of Liability.
601 | 
602 |   IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
610 | SUCH DAMAGES.
611 | 
612 |   17. Interpretation of Sections 15 and 16.
613 | 
614 |   If the disclaimer of warranty and limitation of liability provided
615 | above cannot be given local legal effect according to their terms,
616 | reviewing courts shall apply local law that most closely approximates
617 | an absolute waiver of all civil liability in connection with the
618 | Program, unless a warranty or assumption of liability accompanies a
619 | copy of the Program in return for a fee.
620 | 
621 |                      END OF TERMS AND CONDITIONS
622 | 
623 |             How to Apply These Terms to Your New Programs
624 | 
625 |   If you develop a new program, and you want it to be of the greatest
626 | possible use to the public, the best way to achieve this is to make it
627 | free software which everyone can redistribute and change under these terms.
628 | 
629 |   To do so, attach the following notices to the program.  It is safest
630 | to attach them to the start of each source file to most effectively
631 | state the exclusion of warranty; and each file should have at least
632 | the "copyright" line and a pointer to where the full notice is found.
633 | 
634 |     
635 |     Copyright (C)   
636 | 
637 |     This program is free software: you can redistribute it and/or modify
638 |     it under the terms of the GNU General Public License as published by
639 |     the Free Software Foundation, either version 3 of the License, or
640 |     (at your option) any later version.
641 | 
642 |     This program is distributed in the hope that it will be useful,
643 |     but WITHOUT ANY WARRANTY; without even the implied warranty of
644 |     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
645 |     GNU General Public License for more details.
646 | 
647 |     You should have received a copy of the GNU General Public License
648 |     along with this program.  If not, see .
649 | 
650 | Also add information on how to contact you by electronic and paper mail.
651 | 
652 |   If the program does terminal interaction, make it output a short
653 | notice like this when it starts in an interactive mode:
654 | 
655 |       Copyright (C)   
656 |     This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
657 |     This is free software, and you are welcome to redistribute it
658 |     under certain conditions; type `show c' for details.
659 | 
660 | The hypothetical commands `show w' and `show c' should show the appropriate
661 | parts of the General Public License.  Of course, your program's commands
662 | might be different; for a GUI interface, you would use an "about box".
663 | 
664 |   You should also get your employer (if you work as a programmer) or school,
665 | if any, to sign a "copyright disclaimer" for the program, if necessary.
666 | For more information on this, and how to apply and follow the GNU GPL, see
667 | .
668 | 
669 |   The GNU General Public License does not permit incorporating your program
670 | into proprietary programs.  If your program is a subroutine library, you
671 | may consider it more useful to permit linking proprietary applications with
672 | the library.  If this is what you want to do, use the GNU Lesser General
673 | Public License instead of this License.  But first, please read
674 | .
675 | 


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