diff options
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/allocine.py | 56 |
1 files changed, 43 insertions, 13 deletions
diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py index b292ffdd9..517b06def 100644 --- a/youtube_dl/extractor/allocine.py +++ b/youtube_dl/extractor/allocine.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + remove_end, qualities, url_basename, ) @@ -46,7 +47,14 @@ class AllocineIE(InfoExtractor): }, }, { 'url': 'http://www.allocine.fr/video/video-19550147/', - 'only_matching': True, + 'md5': '3566c0668c0235e2d224fd8edb389f67', + 'info_dict': { + 'id': '19550147', + 'ext': 'mp4', + 'title': 'Faux Raccord N°123 - Les gaffes de Cliffhanger', + 'description': 'md5:bc734b83ffa2d8a12188d9eb48bb6354', + 'thumbnail': 're:http://.*\.jpg', + }, }] def _real_extract(self, url): @@ -54,26 +62,48 @@ class AllocineIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + formats = [] + quality = qualities(['ld', 'md', 'hd']) + model = self._html_search_regex( - r'data-model="([^"]+)"', webpage, 'data model') - model_data = self._parse_json(model, display_id) + r'data-model="([^"]+)"', webpage, 'data model', default=None) + if model: + model_data = self._parse_json(model, display_id) - quality = qualities(['ld', 'md', 'hd']) + for video_url in model_data['sources'].values(): + video_id, format_id = url_basename(video_url).split('_')[:2] + formats.append({ + 'format_id': format_id, + 'quality': quality(format_id), + 'url': video_url, + }) + + title = model_data['title'] + else: + video_id = display_id + media_data = self._download_json( + 'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id) + for key, value in media_data['video'].items(): + if not key.endswith('Path'): + continue + + format_id = key[:-len('Path')] + formats.append({ + 'format_id': format_id, + 'quality': quality(format_id), + 'url': value, + }) + + title = remove_end(self._html_search_regex( + r'(?s)<title>(.+?)</title>', webpage, 'title' + ).strip(), ' - AlloCiné') - formats = [] - for video_url in model_data['sources'].values(): - video_id, format_id = url_basename(video_url).split('_')[:2] - formats.append({ - 'format_id': format_id, - 'quality': quality(format_id), - 'url': video_url, - }) self._sort_formats(formats) return { 'id': video_id, 'display_id': display_id, - 'title': model_data['title'], + 'title': title, 'thumbnail': self._og_search_thumbnail(webpage), 'formats': formats, 'description': self._og_search_description(webpage), |