_ Git - youtube-dl/blob - youtube_dl/extractor/motherless.py

   1 from __future__ import unicode_literals
   2
   3 import datetime
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urlparse
   8 from ..utils import (
   9     ExtractorError,
  10     InAdvancePagedList,
  11     orderedSet,
  12     str_to_int,
  13     unified_strdate,
  14 )
  15
  16
  17 class MotherlessIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P<id>[A-Z0-9]+)'
  19     _TESTS = [{
  20         'url': 'http://motherless.com/AC3FFE1',
  21         'md5': '310f62e325a9fafe64f68c0bccb6e75f',
  22         'info_dict': {
  23             'id': 'AC3FFE1',
  24             'ext': 'mp4',
  25             'title': 'Fucked in the ass while playing PS3',
  26             'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
  27             'upload_date': '20100913',
  28             'uploader_id': 'famouslyfuckedup',
  29             'thumbnail': r're:http://.*\.jpg',
  30             'age_limit': 18,
  31         }
  32     }, {
  33         'url': 'http://motherless.com/532291B',
  34         'md5': 'bc59a6b47d1f958e61fbd38a4d31b131',
  35         'info_dict': {
  36             'id': '532291B',
  37             'ext': 'mp4',
  38             'title': 'Amazing girl playing the omegle game, PERFECT!',
  39             'categories': ['Amateur', 'webcam', 'omegle', 'pink', 'young', 'masturbate', 'teen',
  40                            'game', 'hairy'],
  41             'upload_date': '20140622',
  42             'uploader_id': 'Sulivana7x',
  43             'thumbnail': r're:http://.*\.jpg',
  44             'age_limit': 18,
  45         },
  46         'skip': '404',
  47     }, {
  48         'url': 'http://motherless.com/g/cosplay/633979F',
  49         'md5': '0b2a43f447a49c3e649c93ad1fafa4a0',
  50         'info_dict': {
  51             'id': '633979F',
  52             'ext': 'mp4',
  53             'title': 'Turtlette',
  54             'categories': ['superheroine heroine  superher'],
  55             'upload_date': '20140827',
  56             'uploader_id': 'shade0230',
  57             'thumbnail': r're:http://.*\.jpg',
  58             'age_limit': 18,
  59         }
  60     }, {
  61         # no keywords
  62         'url': 'http://motherless.com/8B4BBC1',
  63         'only_matching': True,
  64     }]
  65
  66     def _real_extract(self, url):
  67         video_id = self._match_id(url)
  68         webpage = self._download_webpage(url, video_id)
  69
  70         if any(p in webpage for p in (
  71                 '<title>404 - MOTHERLESS.COM<',
  72                 ">The page you're looking for cannot be found.<")):
  73             raise ExtractorError('Video %s does not exist' % video_id, expected=True)
  74
  75         if '>The content you are trying to view is for friends only.' in webpage:
  76             raise ExtractorError('Video %s is for friends only' % video_id, expected=True)
  77
  78         title = self._html_search_regex(
  79             r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
  80         video_url = self._html_search_regex(
  81             r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL')
  82         age_limit = self._rta_search(webpage)
  83         view_count = str_to_int(self._html_search_regex(
  84             r'<strong>Views</strong>\s+([^<]+)<',
  85             webpage, 'view count', fatal=False))
  86         like_count = str_to_int(self._html_search_regex(
  87             r'<strong>Favorited</strong>\s+([^<]+)<',
  88             webpage, 'like count', fatal=False))
  89
  90         upload_date = self._html_search_regex(
  91             r'<strong>Uploaded</strong>\s+([^<]+)<', webpage, 'upload date')
  92         if 'Ago' in upload_date:
  93             days = int(re.search(r'([0-9]+)', upload_date).group(1))
  94             upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
  95         else:
  96             upload_date = unified_strdate(upload_date)
  97
  98         comment_count = webpage.count('class="media-comment-contents"')
  99         uploader_id = self._html_search_regex(
 100             r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
 101             webpage, 'uploader_id')
 102
 103         categories = self._html_search_meta('keywords', webpage, default=None)
 104         if categories:
 105             categories = [cat.strip() for cat in categories.split(',')]
 106
 107         return {
 108             'id': video_id,
 109             'title': title,
 110             'upload_date': upload_date,
 111             'uploader_id': uploader_id,
 112             'thumbnail': self._og_search_thumbnail(webpage),
 113             'categories': categories,
 114             'view_count': view_count,
 115             'like_count': like_count,
 116             'comment_count': comment_count,
 117             'age_limit': age_limit,
 118             'url': video_url,
 119         }
 120
 121
 122 class MotherlessGroupIE(InfoExtractor):
 123     _VALID_URL = 'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[a-z0-9_]+)'
 124     _TESTS = [{
 125         'url': 'http://motherless.com/g/movie_scenes',
 126         'info_dict': {
 127             'id': 'movie_scenes',
 128             'title': 'Movie Scenes',
 129             'description': 'Hot and sexy scenes from "regular" movies... '
 130                            'Beautiful actresses fully nude... A looot of '
 131                            'skin! :)Enjoy!',
 132         },
 133         'playlist_mincount': 662,
 134     }, {
 135         'url': 'http://motherless.com/gv/sex_must_be_funny',
 136         'info_dict': {
 137             'id': 'sex_must_be_funny',
 138             'title': 'Sex must be funny',
 139             'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
 140                            'any kind!'
 141         },
 142         'playlist_mincount': 9,
 143     }]
 144
 145     @classmethod
 146     def suitable(cls, url):
 147         return (False if MotherlessIE.suitable(url)
 148                 else super(MotherlessGroupIE, cls).suitable(url))
 149
 150     def _extract_entries(self, webpage, base):
 151         entries = []
 152         for mobj in re.finditer(
 153                 r'href="(?P<href>/[^"]+)"[^>]*>(?:\s*<img[^>]+alt="[^-]+-\s(?P<title>[^"]+)")?',
 154                 webpage):
 155             video_url = compat_urlparse.urljoin(base, mobj.group('href'))
 156             if not MotherlessIE.suitable(video_url):
 157                 continue
 158             video_id = MotherlessIE._match_id(video_url)
 159             title = mobj.group('title')
 160             entries.append(self.url_result(
 161                 video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
 162                 video_title=title))
 163         # Alternative fallback
 164         if not entries:
 165             entries = [
 166                 self.url_result(
 167                     compat_urlparse.urljoin(base, '/' + video_id),
 168                     ie=MotherlessIE.ie_key(), video_id=video_id)
 169                 for video_id in orderedSet(re.findall(
 170                     r'data-codename=["\']([A-Z0-9]+)', webpage))]
 171         return entries
 172
 173     def _real_extract(self, url):
 174         group_id = self._match_id(url)
 175         page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
 176         webpage = self._download_webpage(page_url, group_id)
 177         title = self._search_regex(
 178             r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
 179         description = self._html_search_meta(
 180             'description', webpage, fatal=False)
 181         page_count = self._int(self._search_regex(
 182             r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
 183             webpage, 'page_count'), 'page_count')
 184         PAGE_SIZE = 80
 185
 186         def _get_page(idx):
 187             webpage = self._download_webpage(
 188                 page_url, group_id, query={'page': idx + 1},
 189                 note='Downloading page %d/%d' % (idx + 1, page_count)
 190             )
 191             for entry in self._extract_entries(webpage, url):
 192                 yield entry
 193
 194         playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 195
 196         return {
 197             '_type': 'playlist',
 198             'id': group_id,
 199             'title': title,
 200             'description': description,
 201             'entries': playlist
 202         }