_ 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     clean_html,
   8     determine_ext,
   9     int_or_none,
  10     js_to_json,
  11     parse_duration,
  12 )
  13
  14
  15 class SnagFilmsEmbedIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
  17     _TESTS = [{
  18         'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
  19         'md5': '2924e9215c6eff7a55ed35b72276bd93',
  20         'info_dict': {
  21             'id': '74849a00-85a9-11e1-9660-123139220831',
  22             'ext': 'mp4',
  23             'title': '#whilewewatch',
  24         }
  25     }, {
  26         'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         webpage = self._download_webpage(url, video_id)
  34
  35         formats = []
  36         for source in self._parse_json(js_to_json(self._search_regex(
  37                 r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
  38             file_ = source.get('file')
  39             if not file_:
  40                 continue
  41             type_ = source.get('type')
  42             format_id = source.get('label')
  43             ext = determine_ext(file_)
  44             if any(_ == 'm3u8' for _ in (type_, ext)):
  45                 formats.extend(self._extract_m3u8_formats(
  46                     file_, video_id, 'mp4', m3u8_id='hls'))
  47             else:
  48                 bitrate = int_or_none(self._search_regex(
  49                     r'(\d+)kbps', file_, 'bitrate', default=None))
  50                 height = int_or_none(self._search_regex(
  51                     r'^(\d+)[pP]$', format_id, 'height', default=None))
  52                 formats.append({
  53                     'url': file_,
  54                     'format_id': format_id,
  55                     'tbr': bitrate,
  56                     'height': height,
  57                 })
  58         self._sort_formats(formats)
  59
  60         title = self._search_regex(
  61             [r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
  62             webpage, 'title')
  63
  64         return {
  65             'id': video_id,
  66             'title': title,
  67             'formats': formats,
  68         }
  69
  70
  71 class SnagFilmsIE(InfoExtractor):
  72     _VALID_URL = r'https?://(?:www\.)?snagfilms\.com/films/title/(?P<id>[^/]+)'
  73     _TEST = {
  74         'url': 'http://www.snagfilms.com/films/title/lost_for_life',
  75         'md5': '19844f897b35af219773fd63bdec2942',
  76         'info_dict': {
  77             'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
  78             'display_id': 'lost_for_life',
  79             'ext': 'mp4',
  80             'title': 'Lost for Life',
  81             'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
  82             'thumbnail': 're:^https?://.*\.jpg',
  83             'duration': 4489,
  84             'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
  85         }
  86     }
  87
  88     def _real_extract(self, url):
  89         display_id = self._match_id(url)
  90
  91         webpage = self._download_webpage(url, display_id)
  92
  93         film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
  94
  95         snag = self._parse_json(
  96             self._search_regex(
  97                 'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
  98             display_id)
  99
 100         for item in snag:
 101             if item.get('data', {}).get('film', {}).get('id') == film_id:
 102                 data = item['data']['film']
 103                 title = data['title']
 104                 description = clean_html(data.get('synopsis'))
 105                 thumbnail = data.get('image')
 106                 duration = int_or_none(data.get('duration') or data.get('runtime'))
 107                 categories = [
 108                     category['title'] for category in data.get('categories', [])
 109                     if category.get('title')]
 110                 break
 111         else:
 112             title = self._search_regex(
 113                 r'itemprop="title">([^<]+)<', webpage, 'title')
 114             description = self._html_search_regex(
 115                 r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
 116                 webpage, 'description', default=None) or self._og_search_description(webpage)
 117             thumbnail = self._og_search_thumbnail(webpage)
 118             duration = parse_duration(self._search_regex(
 119                 r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
 120                 webpage, 'duration', fatal=False))
 121             categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
 122
 123         return {
 124             '_type': 'url_transparent',
 125             'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
 126             'id': film_id,
 127             'display_id': display_id,
 128             'title': title,
 129             'description': description,
 130             'thumbnail': thumbnail,
 131             'duration': duration,
 132             'categories': categories,
 133         }