- _VALID_URL = r'(?:https?://)?(?:www.)?snagfilms\.com/films/title/(?P<display_id>.+?)(?:/|$)'
- _TEST = {
- 'url': 'http://www.snagfilms.com/films/title/lost_for_life',
- 'info_dict':
- {
- 'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
- 'display_id': 'lost_for_life',
- 'ext': 'mp4',
- 'title': 'Lost for Life',
- 'duration': 4489,
- 'description': 'In the United States, more than 2500 individuals are serving life-without-parole sentences for crimes they committed when they were seventeen years old or younger. Children as young as thirteen are among the thousands serving these sentences. Directed by Joshua Rofé (who spent four intensive years on the project), LOST FOR LIFE tells the stories of these individuals, their families and the families of juvenile murder victims. This searingly powerful documentary tackles this contentious issue from multiple perspectives and explores the complexity of the lives of those affected. What is justice when a kid kills? Can a horrific act place a life beyond redemption? Could you forgive?<br />',
- 'categories': ['Documentary','Crime','Award Winning','Festivals']
- }
- }
-
- def _real_extract(self, url):
- display_id = self._search_regex(
- self._VALID_URL,
- url,
- 'display_id',
- group='display_id'
- )
- webpage = self._download_webpage(url, display_id)
-
- json_data = self._parse_json(self._html_search_regex(
- r'"data":{"film":(?P<data>{.*?}})}',
- webpage,
- 'data',
- group='data'
- ), display_id)
- title = json_data['title']
- video_id = json_data['id']
- duration = int(json_data['duration'])
- description = json_data['synopsis']
- categories = [category['title'] for category in json_data['categories']]
-
- embed_webpage = self._download_webpage('http://www.snagfilms.com/embed/player?filmId=' + video_id, video_id)
- sources = self._parse_json(js_to_json(self._html_search_regex(
- r'sources: (?P<sources>\[.*?\])',
- embed_webpage,
- 'sources',
- group='sources',
- flags=DOTALL
- )), video_id)
-
- formats = []
- for source in sources:
- if source['type'] == 'm3u8':
- formats.extend(self._extract_m3u8_formats(source['file'], video_id))
- else:
- formats.append({'url': source['file'],'ext': source['type'], 'resolution': source['label']})
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'display_id': display_id,
- 'title': title,
- 'duration': duration,
- 'description': description,
- 'categories': categories,
- 'formats': formats,
- }
+ _VALID_URL = r'https?://(?:www\.)?snagfilms\.com/(?:films/title|show)/(?P<id>[^?#]+)'
+ _TESTS = [{
+ 'url': 'http://www.snagfilms.com/films/title/lost_for_life',
+ 'md5': '19844f897b35af219773fd63bdec2942',
+ 'info_dict': {
+ 'id': '0000014c-de2f-d5d6-abcf-ffef58af0017',
+ 'display_id': 'lost_for_life',
+ 'ext': 'mp4',
+ 'title': 'Lost for Life',
+ 'description': 'md5:fbdacc8bb6b455e464aaf98bc02e1c82',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'duration': 4489,
+ 'categories': ['Documentary', 'Crime', 'Award Winning', 'Festivals']
+ }
+ }, {
+ 'url': 'http://www.snagfilms.com/show/the_world_cut_project/india',
+ 'md5': 'e6292e5b837642bbda82d7f8bf3fbdfd',
+ 'info_dict': {
+ 'id': '00000145-d75c-d96e-a9c7-ff5c67b20000',
+ 'display_id': 'the_world_cut_project/india',
+ 'ext': 'mp4',
+ 'title': 'India',
+ 'description': 'md5:5c168c5a8f4719c146aad2e0dfac6f5f',
+ 'thumbnail': 're:^https?://.*\.jpg',
+ 'duration': 979,
+ 'categories': ['Documentary', 'Sports', 'Politics']
+ }
+ }, {
+ # Film is not playable in your area.
+ 'url': 'http://www.snagfilms.com/films/title/inside_mecca',
+ 'only_matching': True,
+ }, {
+ # Film is not available.
+ 'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, display_id)
+
+ if ">Sorry, the Film you're looking for is not available.<" in webpage:
+ raise ExtractorError(
+ 'Film %s is not available.' % display_id, expected=True)
+
+ film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
+
+ snag = self._parse_json(
+ self._search_regex(
+ 'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag'),
+ display_id)
+
+ for item in snag:
+ if item.get('data', {}).get('film', {}).get('id') == film_id:
+ data = item['data']['film']
+ title = data['title']
+ description = clean_html(data.get('synopsis'))
+ thumbnail = data.get('image')
+ duration = int_or_none(data.get('duration') or data.get('runtime'))
+ categories = [
+ category['title'] for category in data.get('categories', [])
+ if category.get('title')]
+ break
+ else:
+ title = self._search_regex(
+ r'itemprop="title">([^<]+)<', webpage, 'title')
+ description = self._html_search_regex(
+ r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
+ webpage, 'description', default=None) or self._og_search_description(webpage)
+ thumbnail = self._og_search_thumbnail(webpage)
+ duration = parse_duration(self._search_regex(
+ r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
+ webpage, 'duration', fatal=False))
+ categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
+
+ return {
+ '_type': 'url_transparent',
+ 'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
+ 'id': film_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ 'categories': categories,
+ }