Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-07 07:39:59 +08:00
Code Issues Releases Wiki Activity

Setting GEO bypass

Browse Source 
Removing ISM since failing on many old videos
Sorting formats
Adding tests
This commit is contained in:
Frederic Bournival 2020-04-19 21:03:38 -04:00
parent 2a48d8cc93
commit 8f91c383bf
1 changed files with 34 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
youtube_dl/extractor/tv5unisca.py
View File

@ -13,8 +13,33 @@ import re
class TV5UnisCaIE(InfoExtractor): class TV5UnisCaIE(InfoExtractor):
IE_DESC = 'TV5UNISCA' IE_DESC = 'TV5UNISCA'
_VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/(?P<id>[^?#]+)' _VALID_URL = r'https?://(?:www\.)?tv5unis\.ca/videos/(?P<id>[^?#]+)'
_TESTS = [] _TESTS = [{
_GEO_COUNTRIES = ['CA', 'FR'] 'url': 'https://www.tv5unis.ca/videos/expedition-kayak/saisons/1/episodes/2',
'info_dict': {
'id': 'expedition-kayak/saisons/1/episodes/2',
'episode_number': 2,
'season_number': 1,
'ext': 'm3u8',
'title': 'Expédition kayak - Gaspésie 2',
'description': 'md5:aecf01897141d3997f10685b3f2662ef',
'upload_date': '20200417',
'timestamp': 1587085203,
}
}, {
'url': 'https://www.tv5unis.ca/videos/la-bataille-de-notre-dame',
'info_dict': {
'id': 'la-bataille-de-notre-dame',
'ext': 'm3u8',
'title': 'La bataille de Notre-Dame',
'description': 'md5:b69a25dbe9b1880eadad219af7372a7c',
'upload_date': '20200414',
'timestamp': 1586824384,
},
'params': {
'skip_download': True,
}
}]
_GEO_BYPASS = False
def _real_extract(self, url): def _real_extract(self, url):
@ -22,7 +47,7 @@ class TV5UnisCaIE(InfoExtractor):
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
next_data_dict = self._parse_json( next_data_dict = self._parse_json(
get_element_by_id('__NEXT_DATA__', webpage), display_id)\ get_element_by_id('__NEXT_DATA__', webpage), display_id) \
.get('props').get('apolloState') .get('props').get('apolloState')
info_dict = self._json_ld( info_dict = self._json_ld(
@ -30,6 +55,11 @@ class TV5UnisCaIE(InfoExtractor):
display_id display_id
) )
if info_dict.get('season', ''):
info_dict['title'] = ' - '.join((info_dict.get('season', ''), info_dict.get('episode', '')))
info_dict['id'] = info_dict['display_id'] = display_id
formats = [] formats = []
for key in filter(lambda k: re.match(r'\$Video:\d+\.encodings\.', k), next_data_dict.keys()): for key in filter(lambda k: re.match(r'\$Video:\d+\.encodings\.', k), next_data_dict.keys()):
url = next_data_dict[key].get('url') url = next_data_dict[key].get('url')
@ -37,15 +67,13 @@ class TV5UnisCaIE(InfoExtractor):
continue continue
if url.endswith('.m3u8'): if url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(url, display_id)) formats.extend(self._extract_m3u8_formats(url, display_id))
if url.endswith('.ism/manifest'):
formats.extend(self._extract_ism_formats(url, display_id, ism_id='mss', fatal=False))
if url.endswith('.mp4'): if url.endswith('.mp4'):
formats.append({ formats.append({
'url': url, 'url': url,
'format_id': 'http' 'format_id': 'http'
}) })
info_dict['id'] = info_dict['display_id'] = display_id self._sort_formats(formats)
info_dict['formats'] = formats info_dict['formats'] = formats
return info_dict return info_dict