Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/viewlift.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     ExtractorError,
   8     clean_html,
   9     determine_ext,
  10     int_or_none,
  11     js_to_json,
  12     parse_duration,
  13 )
  14
  15
  16 class ViewLiftBaseIE(InfoExtractor):
  17     _DOMAINS_REGEX = '(?:snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|monumentalsportsnetwork|vayafilm)\.com|kesari\.tv'
  18
  19
  20 class ViewLiftEmbedIE(ViewLiftBaseIE):
  21     _VALID_URL = r'https?://(?:(?:www|embed)\.)?(?:%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})' % ViewLiftBaseIE._DOMAINS_REGEX
  22     _TESTS = [{
  23         'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
  24         'md5': '2924e9215c6eff7a55ed35b72276bd93',
  25         'info_dict': {
  26             'id': '74849a00-85a9-11e1-9660-123139220831',
  27             'ext': 'mp4',
  28             'title': '#whilewewatch',
  29         }
  30     }, {
  31         # invalid labels, 360p is better that 480p
  32         'url': 'http://www.snagfilms.com/embed/player?filmId=17ca0950-a74a-11e0-a92a-0026bb61d036',
  33         'md5': '882fca19b9eb27ef865efeeaed376a48',
  34         'info_dict': {
  35             'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
  36             'ext': 'mp4',
  37             'title': 'Life in Limbo',
  38         }
  39     }, {
  40         'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
  41         'only_matching': True,
  42     }]
  43
  44     @staticmethod
  45     def _extract_url(webpage):
  46         mobj = re.search(
  47             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?(?:%s)/embed/player.+?)\1' % ViewLiftBaseIE._DOMAINS_REGEX,
  48             webpage)
  49         if mobj:
  50             return mobj.group('url')
  51
  52     def _real_extract(self, url):
  53         video_id = self._match_id(url)
  54
  55         webpage = self._download_webpage(url, video_id)
  56
  57         if '>This film is not playable in your area.<' in webpage:
  58             raise ExtractorError(
  59                 'Film %s is not playable in your area.' % video_id, expected=True)
  60
  61         formats = []
  62         has_bitrate = False
  63         for source in self._parse_json(js_to_json(self._search_regex(
  64                 r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
  65             file_ = source.get('file')
  66             if not file_:
  67                 continue
  68             type_ = source.get('type')
  69             ext = determine_ext(file_)
  70             format_id = source.get('label') or ext
  71             if all(v == 'm3u8' or v == 'hls' for v in (type_, ext)):
  72                 formats.extend(self._extract_m3u8_formats(
  73                     file_, video_id, 'mp4', m3u8_id='hls'))
  74             else:
  75                 bitrate = int_or_none(self._search_regex(
  76                     [r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext],
  77                     file_, 'bitrate', default=None))
  78                 if not has_bitrate and bitrate:
  79                     has_bitrate = True
  80                 height = int_or_none(self._search_regex(
  81                     r'^(\d+)[pP]$', format_id, 'height', default=None))
  82                 formats.append({
  83                     'url': file_,
  84                     'format_id': 'http-%s%s' % (format_id, ('-%dk' % bitrate if bitrate else '')),
  85                     'tbr': bitrate,
  86                     'height': height,
  87                 })
  88         field_preference = None if has_bitrate else ('height', 'tbr', 'format_id')
  89         self._sort_formats(formats, field_preference)
  90
  91         title = self._search_regex(
  92             [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
  93             webpage, 'title')
  94
  95         return {
  96             'id': video_id,
  97             'title': title,
  98             'formats': formats,
  99         }
 100
 101
 102 class ViewLiftIE(ViewLiftBaseIE):
 103     _VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)/(?:films/title|show|(?:news/)?videos?)/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX
 104     _TESTS = [{
 105         'url': 'http://www.snagfilms.com/films/title/lost_for_life',
 106         'md5': '19844f897b35af219773fd63bdec2942',
 107         'info_dict': {
 108             'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
 109             'display_id': 'lost_for_life',
 110             'ext': 'mp4',
 111             'title': 'Lost for Life',
 112             'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
 113             'thumbnail': 're:^https?://.*\.jpg',
 114             'duration': 4489,
 115             'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
 116         }
 117     }, {
 118         'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
 119         'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
 120         'info_dict': {
 121             'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
 122             'display_id': 'the_world_cut_project/india',
 123             'ext': 'mp4',
 124             'title': 'India',
 125             'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
 126             'thumbnail': 're:^https?://.*\.jpg',
 127             'duration': 979,
 128             'categories': ['Documentary', 'Sports', 'Politics']
 129         }
 130     }, {
 131         # Film is not playable in your area.
 132         'url': 'http://www.snagfilms.com/films/title/inside_mecca',
 133         'only_matching': True,
 134     }, {
 135         # Film is not available.
 136         'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
 137         'only_matching': True,
 138     }, {
 139         'url': 'http://www.winnersview.com/videos/the-good-son',
 140         'only_matching': True,
 141     }, {
 142         'url': 'http://www.kesari.tv/news/video/1461919076414',
 143         'only_matching': True,
 144     }, {
 145         # Was once Kaltura embed
 146         'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
 147         'only_matching': True,
 148     }]
 149
 150     def _real_extract(self, url):
 151         domain, display_id = re.match(self._VALID_URL, url).groups()
 152
 153         webpage = self._download_webpage(url, display_id)
 154
 155         if ">Sorry, the Film you're looking for is not available.<" in webpage:
 156             raise ExtractorError(
 157                 'Film %s is not available.' % display_id, expected=True)
 158
 159         film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
 160
 161         snag = self._parse_json(
 162             self._search_regex(
 163                 'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
 164             display_id)
 165
 166         for item in snag:
 167             if item.get('data', {}).get('film', {}).get('id') == film_id:
 168                 data = item['data']['film']
 169                 title = data['title']
 170                 description = clean_html(data.get('synopsis'))
 171                 thumbnail = data.get('image')
 172                 duration = int_or_none(data.get('duration') or data.get('runtime'))
 173                 categories = [
 174                     category['title'] for category in data.get('categories', [])
 175                     if category.get('title')]
 176                 break
 177         else:
 178             title = self._search_regex(
 179                 r'itemprop="title">([^<]+)<', webpage, 'title')
 180             description = self._html_search_regex(
 181                 r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
 182                 webpage, 'description', default=None) or self._og_search_description(webpage)
 183             thumbnail = self._og_search_thumbnail(webpage)
 184             duration = parse_duration(self._search_regex(
 185                 r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
 186                 webpage, 'duration', fatal=False))
 187             categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
 188
 189         return {
 190             '_type': 'url_transparent',
 191             'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
 192             'id': film_id,
 193             'display_id': display_id,
 194             'title': title,
 195             'description': description,
 196             'thumbnail': thumbnail,
 197             'duration': duration,
 198             'categories': categories,
 199             'ie_key': 'ViewLiftEmbed',
 200         }