_ Git - youtube-dl/blob - youtube_dl/extractor/snagfilms.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 SnagFilmsEmbedIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
  18     _TESTS = [{
  19         'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
  20         'md5': '2924e9215c6eff7a55ed35b72276bd93',
  21         'info_dict': {
  22             'id': '74849a00-85a9-11e1-9660-123139220831',
  23             'ext': 'mp4',
  24             'title': '#whilewewatch',
  25         }
  26     }, {
  27         'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
  28         'only_matching': True,
  29     }]
  30
  31     @staticmethod
  32     def _extract_url(webpage):
  33         mobj = re.search(
  34             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?snagfilms\.com/embed/player.+?)\1',
  35             webpage)
  36         if mobj:
  37             return mobj.group('url')
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         webpage = self._download_webpage(url, video_id)
  43
  44         if '>This film is not playable in your area.<' in webpage:
  45             raise ExtractorError(
  46                 'Film %s is not playable in your area.' % video_id, expected=True)
  47
  48         formats = []
  49         for source in self._parse_json(js_to_json(self._search_regex(
  50                 r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
  51             file_ = source.get('file')
  52             if not file_:
  53                 continue
  54             type_ = source.get('type')
  55             format_id = source.get('label')
  56             ext = determine_ext(file_)
  57             if any(_ == 'm3u8' for _ in (type_, ext)):
  58                 formats.extend(self._extract_m3u8_formats(
  59                     file_, video_id, 'mp4', m3u8_id='hls'))
  60             else:
  61                 bitrate = int_or_none(self._search_regex(
  62                     r'(\d+)kbps', file_, 'bitrate', default=None))
  63                 height = int_or_none(self._search_regex(
  64                     r'^(\d+)[pP]$', format_id, 'height', default=None))
  65                 formats.append({
  66                     'url': file_,
  67                     'format_id': format_id,
  68                     'tbr': bitrate,
  69                     'height': height,
  70                 })
  71         self._sort_formats(formats)
  72
  73         title = self._search_regex(
  74             [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
  75             webpage, 'title')
  76
  77         return {
  78             'id': video_id,
  79             'title': title,
  80             'formats': formats,
  81         }
  82
  83
  84 class SnagFilmsIE(InfoExtractor):
  85     _VALID_URL = r'https?://(?:www\.)?snagfilms\.com/(?:films/title|show)/(?P<id>[^?#]+)'
  86     _TESTS = [{
  87         'url': 'http://www.snagfilms.com/films/title/lost_for_life',
  88         'md5': '19844f897b35af219773fd63bdec2942',
  89         'info_dict': {
  90             'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
  91             'display_id': 'lost_for_life',
  92             'ext': 'mp4',
  93             'title': 'Lost for Life',
  94             'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
  95             'thumbnail': 're:^https?://.*\.jpg',
  96             'duration': 4489,
  97             'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
  98         }
  99     }, {
 100         'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
 101         'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
 102         'info_dict': {
 103             'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
 104             'display_id': 'the_world_cut_project/india',
 105             'ext': 'mp4',
 106             'title': 'India',
 107             'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
 108             'thumbnail': 're:^https?://.*\.jpg',
 109             'duration': 979,
 110             'categories': ['Documentary', 'Sports', 'Politics']
 111         }
 112     }, {
 113         # Film is not playable in your area.
 114         'url': 'http://www.snagfilms.com/films/title/inside_mecca',
 115         'only_matching': True,
 116     }, {
 117         # Film is not available.
 118         'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
 119         'only_matching': True,
 120     }]
 121
 122     def _real_extract(self, url):
 123         display_id = self._match_id(url)
 124
 125         webpage = self._download_webpage(url, display_id)
 126
 127         if ">Sorry, the Film you're looking for is not available.<" in webpage:
 128             raise ExtractorError(
 129                 'Film %s is not available.' % display_id, expected=True)
 130
 131         film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
 132
 133         snag = self._parse_json(
 134             self._search_regex(
 135                 'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
 136             display_id)
 137
 138         for item in snag:
 139             if item.get('data', {}).get('film', {}).get('id') == film_id:
 140                 data = item['data']['film']
 141                 title = data['title']
 142                 description = clean_html(data.get('synopsis'))
 143                 thumbnail = data.get('image')
 144                 duration = int_or_none(data.get('duration') or data.get('runtime'))
 145                 categories = [
 146                     category['title'] for category in data.get('categories', [])
 147                     if category.get('title')]
 148                 break
 149         else:
 150             title = self._search_regex(
 151                 r'itemprop="title">([^<]+)<', webpage, 'title')
 152             description = self._html_search_regex(
 153                 r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
 154                 webpage, 'description', default=None) or self._og_search_description(webpage)
 155             thumbnail = self._og_search_thumbnail(webpage)
 156             duration = parse_duration(self._search_regex(
 157                 r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
 158                 webpage, 'duration', fatal=False))
 159             categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
 160
 161         return {
 162             '_type': 'url_transparent',
 163             'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
 164             'id': film_id,
 165             'display_id': display_id,
 166             'title': title,
 167             'description': description,
 168             'thumbnail': thumbnail,
 169             'duration': duration,
 170             'categories': categories,
 171         }