etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-03 03:57:26 +00:00
Code Issues Projects Releases Wiki Activity

[gedi] added huffingtonpost, added embeds

Browse source
This commit is contained in:
nixxo 2020-11-09 09:16:37 +01:00
parent 165ce9f773
commit 902784a2a9
3 changed files with 100 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
youtube_dlc/extractor/extractors.py
View file

@ -414,7 +414,10 @@
from .gaskrank import GaskrankIE
from .gazeta import GazetaIE
from .gdcvault import GDCVaultIE
from .gedi import GediIE
from .gedi import (
GediIE,
GediEmbedsIE,
)
from .generic import GenericIE
from .gfycat import GfycatIE
from .giantbomb import GiantBombIE

89
youtube_dlc/extractor/gedi.py
View file

@ -5,6 +5,11 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
base_url,
url_basename,
urljoin,
)
class GediBaseIE(InfoExtractor):
@ -109,6 +114,7 @@ class GediIE(GediBaseIE):
(?:
(?:espresso\.)?repubblica
|lastampa
|huffingtonpost
|ilsecoloxix
|iltirreno
|messaggeroveneto
@ -175,3 +181,86 @@ class GediIE(GediBaseIE):
'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
},
}]
class GediEmbedsIE(GediBaseIE):
_VALID_URL = r'''(?x)https?://video\.
(?:
(?:espresso\.)?repubblica
|lastampa
|huffingtonpost
|ilsecoloxix
|iltirreno
|messaggeroveneto
|ilpiccolo
|gazzettadimantova
|mattinopadova
|laprovinciapavese
|tribunatreviso
|nuovavenezia
|gazzettadimodena
|lanuovaferrara
|corrierealpi
|lasentinella
)
(?:\.gelocal)?\.it/embed/.+?/(?P<id>[\d/]+)(?:\?|\&|$)'''
_TESTS = [{
'url': 'https://video.huffingtonpost.it/embed/politica/cotticelli-non-so-cosa-mi-sia-successo-sto-cercando-di-capire-se-ho-avuto-un-malore/29312/29276?responsive=true&el=video971040871621586700',
'md5': '0391c2c83c6506581003aaf0255889c0',
'info_dict': {
'id': '14772/14870',
'ext': 'mp4',
'title': 'Festival EMERGENCY, Villa: «La buona informazione aiuta la salute» (14772-14870)',
'description': 'md5:2bce954d278248f3c950be355b7c2226',
'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
},
}]
@staticmethod
def _sanitize_urls(urls):
# add protocol if missing
for i, e in enumerate(urls):
if e.startswith('//'):
urls[i] = 'https:%s' % e
# clean iframes urls
for i, e in enumerate(urls):
urls[i] = urljoin(base_url(e), url_basename(e))
return urls
@staticmethod
def _extract_urls(webpage):
entries = [
mobj.group('url')
for mobj in re.finditer(r'''(?x)
(?:
data-frame-src=|
<iframe[^\n]+src=
)
(["'])
(?P<url>https?://video\.
(?:
(?:espresso\.)?repubblica
|lastampa
|huffingtonpost
|ilsecoloxix
|iltirreno
|messaggeroveneto
|ilpiccolo
|gazzettadimantova
|mattinopadova
|laprovinciapavese
|tribunatreviso
|nuovavenezia
|gazzettadimodena
|lanuovaferrara
|corrierealpi
|lasentinella
)
(?:\.gelocal)?\.it/embed/.+?)
\1''', webpage)]
return GediEmbedsIE._sanitize_urls(entries)
@staticmethod
def _extract_url(webpage):
urls = GediEmbedsIE._extract_urls(webpage)
return urls[0] if urls else None

7
youtube_dlc/extractor/generic.py
View file

@ -119,6 +119,7 @@
from .zype import ZypeIE
from .odnoklassniki import OdnoklassnikiIE
from .kinja import KinjaEmbedIE
from .gedi import GediEmbedsIE
class GenericIE(InfoExtractor):
@ -3213,6 +3214,12 @@ def _real_extract(self, url):
return self.playlist_from_matches(
zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
# Look for RCS media group embeds
gedi_urls = GediEmbedsIE._extract_urls(webpage)
if gedi_urls:
return self.playlist_from_matches(
gedi_urls, video_id, video_title, ie=GediEmbedsIE.ie_key())
# Look for HTML5 media
entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
if entries: