formats = []
for platform in ('mon', 'flash', 'native'):
- headers = {}
- # TODO: rename --cn-verification-proxy
- cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
- if cn_verification_proxy:
- headers['Ytdl-request-proxy'] = cn_verification_proxy
-
relinker = self._download_xml(
relinker_url, video_id,
note='Downloading XML metadata for platform %s' % platform,
transform_source=fix_xml_ampersands,
- query={'output': 45, 'pl': platform}, headers=headers)
+ query={'output': 45, 'pl': platform},
+ headers=self.geo_verification_headers())
media_url = find_xpath_attr(relinker, './url', 'type', 'content').text
if media_url == 'http://download.rai.it/video_no_available.mp4':
return formats
+ def _extract_from_content_id(self, content_id, base_url):
+ media = self._download_json(
+ 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id,
+ content_id, 'Downloading video JSON')
+
+ thumbnails = []
+ for image_type in ('image', 'image_medium', 'image_300'):
+ thumbnail_url = media.get(image_type)
+ if thumbnail_url:
+ thumbnails.append({
+ 'url': compat_urlparse.urljoin(base_url, thumbnail_url),
+ })
+
+ formats = []
+ media_type = media['type']
+ if 'Audio' in media_type:
+ formats.append({
+ 'format_id': media.get('formatoAudio'),
+ 'url': media['audioUrl'],
+ 'ext': media.get('formatoAudio'),
+ })
+ elif 'Video' in media_type:
+ formats.extend(self._extract_relinker_formats(media['mediaUri'], content_id))
+ self._sort_formats(formats)
+ else:
+ raise ExtractorError('not a media file')
+
+ subtitles = {}
+ captions = media.get('subtitlesUrl')
+ if captions:
+ STL_EXT = '.stl'
+ SRT_EXT = '.srt'
+ if captions.endswith(STL_EXT):
+ captions = captions[:-len(STL_EXT)] + SRT_EXT
+ subtitles['it'] = [{
+ 'ext': 'srt',
+ 'url': captions,
+ }]
+
+ return {
+ 'id': content_id,
+ 'title': media['name'],
+ 'description': media.get('desc'),
+ 'thumbnails': thumbnails,
+ 'uploader': media.get('author'),
+ 'upload_date': unified_strdate(media.get('date')),
+ 'duration': parse_duration(media.get('length')),
+ 'formats': formats,
+ 'subtitles': subtitles,
+ }
+
class RaiTVIE(RaiBaseIE):
_VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+(?:media|ondemand)/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
'upload_date': '20140407',
'duration': 6160,
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'thumbnail': r're:^https?://.*\.jpg$',
}
},
{
'title': 'TG PRIMO TEMPO',
'upload_date': '20140612',
'duration': 1758,
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'thumbnail': r're:^https?://.*\.jpg$',
},
'skip': 'Geo-restricted to Italy',
},
'description': 'md5:364b604f7db50594678f483353164fb8',
'upload_date': '20140923',
'duration': 386,
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'thumbnail': r're:^https?://.*\.jpg$',
}
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
- media = self._download_json(
- 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % video_id,
- video_id, 'Downloading video JSON')
-
- thumbnails = []
- for image_type in ('image', 'image_medium', 'image_300'):
- thumbnail_url = media.get(image_type)
- if thumbnail_url:
- thumbnails.append({
- 'url': compat_urlparse.urljoin(url, thumbnail_url),
- })
-
- formats = []
- media_type = media['type']
- if 'Audio' in media_type:
- formats.append({
- 'format_id': media.get('formatoAudio'),
- 'url': media['audioUrl'],
- 'ext': media.get('formatoAudio'),
- })
- elif 'Video' in media_type:
- formats.extend(self._extract_relinker_formats(media['mediaUri'], video_id))
- self._sort_formats(formats)
- else:
- raise ExtractorError('not a media file')
-
- subtitles = {}
- captions = media.get('subtitlesUrl')
- if captions:
- STL_EXT = '.stl'
- SRT_EXT = '.srt'
- if captions.endswith(STL_EXT):
- captions = captions[:-len(STL_EXT)] + SRT_EXT
- subtitles['it'] = [{
- 'ext': 'srt',
- 'url': captions,
- }]
-
- return {
- 'id': video_id,
- 'title': media['name'],
- 'description': media.get('desc'),
- 'thumbnails': thumbnails,
- 'uploader': media.get('author'),
- 'upload_date': unified_strdate(media.get('date')),
- 'duration': parse_duration(media.get('length')),
- 'formats': formats,
- 'subtitles': subtitles,
- }
+ return self._extract_from_content_id(video_id, url)
class RaiIE(RaiBaseIE):
},
},
{
+ # Direct relinker URL
'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
# HDS live stream, MD5 is unstable
'info_dict': {
'title': 'EuroNews',
},
'skip': 'Geo-restricted to Italy',
- }
+ },
+ {
+ # Embedded content item ID
+ 'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
+ 'md5': '84c1135ce960e8822ae63cec34441d63',
+ 'info_dict': {
+ 'id': '0960e765-62c8-474a-ac4b-7eb3e2be39c8',
+ 'ext': 'mp4',
+ 'title': 'TG1 ore 20:00 del 02/07/2016',
+ 'upload_date': '20160702',
+ },
+ },
+ {
+ 'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
+ # HDS live stream, MD5 is unstable
+ 'info_dict': {
+ 'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
+ 'ext': 'flv',
+ 'title': 'La diretta di Rainews24',
+ },
+ },
]
@classmethod
iframe_url = compat_urlparse.urljoin(url, iframe_url)
return self.url_result(iframe_url)
+ content_item_id = self._search_regex(
+ r'initEdizione\((?P<q1>[\'"])ContentItem-(?P<content_id>[^\'"]+)(?P=q1)',
+ webpage, 'content item ID', group='content_id', default=None)
+ if content_item_id:
+ return self._extract_from_content_id(content_item_id, url)
+
relinker_url = compat_urlparse.urljoin(url, self._search_regex(
- r'var\s+videoURL\s*=\s*(?P<q1>[\'"])(?P<url>(https?:)?//mediapolis\.rai\.it/relinker/relinkerServlet\.htm\?cont=\d+)(?P=q1)',
+ r'(?:var\s+videoURL|mediaInfo\.mediaUri)\s*=\s*(?P<q1>[\'"])(?P<url>(https?:)?//mediapolis\.rai\.it/relinker/relinkerServlet\.htm\?cont=\d+)(?P=q1)',
webpage, 'relinker URL', group='url'))
formats = self._extract_relinker_formats(relinker_url, video_id)
self._sort_formats(formats)
projects / youtube-dl.git / blobdiff