paradizelost/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[washingtonpost] Add support for embeds (closes #12699)

Browse Source
This commit is contained in:
John Hawkinson 2017-04-10 01:09:10 -04:00 committed by Sergey M․
parent 27e70a8f6c
commit 557194591a
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
2 changed files with 27 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
youtube_dl/extractor/generic.py
View File

@ -87,6 +87,7 @@ from .videopress import VideoPressIE
from .rutube import RutubeIE from .rutube import RutubeIE
from .limelight import LimelightBaseIE from .limelight import LimelightBaseIE
from .anvato import AnvatoIE from .anvato import AnvatoIE
from .washingtonpost import WashingtonPostIE
class GenericIE(InfoExtractor): class GenericIE(InfoExtractor):
@ -1687,6 +1688,20 @@ class GenericIE(InfoExtractor):
}, },
'playlist_mincount': 4, 'playlist_mincount': 4,
}, },
{
# WashingtonPost embed
'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
'info_dict': {
'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
'ext': 'mp4',
'title': "No one has seen the drama series based on Trump's life \u2014 until now",
'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
'timestamp': 1455216756,
'uploader': 'The Washington Post',
'upload_date': '20160211',
},
'add_ie': [WashingtonPostIE.ie_key()],
},
# { # {
# # TODO: find another test # # TODO: find another test
# # http://schema.org/VideoObject # # http://schema.org/VideoObject
@ -2670,6 +2685,12 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches( return self.playlist_from_matches(
rutube_urls, ie=RutubeIE.ie_key()) rutube_urls, ie=RutubeIE.ie_key())
# Look for WashingtonPost embeds
wapo_urls = WashingtonPostIE._extract_urls(webpage)
if wapo_urls:
return self.playlist_from_matches(
wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
# Looking for http://schema.org/VideoObject # Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld( json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject') webpage, video_id, default={}, expected_type='VideoObject')

6
youtube_dl/extractor/washingtonpost.py
View File

@ -13,6 +13,7 @@ from ..utils import (
class WashingtonPostIE(InfoExtractor): class WashingtonPostIE(InfoExtractor):
IE_NAME = 'washingtonpost' IE_NAME = 'washingtonpost'
_VALID_URL = r'(?:washingtonpost:|https?://(?:www\.)?washingtonpost\.com/video/(?:[^/]+/)*)(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})' _VALID_URL = r'(?:washingtonpost:|https?://(?:www\.)?washingtonpost\.com/video/(?:[^/]+/)*)(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_EMBED_URL = 'https?://(?:www\.)?washingtonpost\.com/video/c/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
_TEST = { _TEST = {
'url': 'https://www.washingtonpost.com/video/c/video/480ba4ee-1ec7-11e6-82c2-a7dcb313287d', 'url': 'https://www.washingtonpost.com/video/c/video/480ba4ee-1ec7-11e6-82c2-a7dcb313287d',
'md5': '6f537e1334b714eb15f9563bd4b9cdfa', 'md5': '6f537e1334b714eb15f9563bd4b9cdfa',
@ -27,6 +28,11 @@ class WashingtonPostIE(InfoExtractor):
}, },
} }
@classmethod
def _extract_urls(cls, webpage):
return re.findall(
r'<iframe[^>]+\bsrc=["\'](%s)' % cls._EMBED_URL, webpage)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
video_data = self._download_json( video_data = self._download_json(