pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-22 20:20:09 +09:00
Code Issues Projects Releases Wiki Activity

[dailymail] Add support for embeds

Browse Source
This commit is contained in:
Sergey M․ 2017-07-09 20:06:24 +07:00
parent 6e925598d6
commit 71a1db8919
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
2 changed files with 35 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
youtube_dl/extractor/dailymail.py
View File

@ -1,6 +1,8 @@
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..utils import ( from ..utils import (
@ -12,8 +14,8 @@ from ..utils import (
class DailyMailIE(InfoExtractor): class DailyMailIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P<id>[0-9]+)'
_TEST = { _TESTS = [{
'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html', 'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html',
'md5': 'f6129624562251f628296c3a9ffde124', 'md5': 'f6129624562251f628296c3a9ffde124',
'info_dict': { 'info_dict': {
@ -22,7 +24,16 @@ class DailyMailIE(InfoExtractor):
'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'', 'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84', 'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
} }
} }, {
'url': 'http://www.dailymail.co.uk/embed/video/1295863.html',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)',
webpage)
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)

21
youtube_dl/extractor/generic.py
View File

@ -57,6 +57,7 @@ from .dailymotion import (
DailymotionIE, DailymotionIE,
DailymotionCloudIE, DailymotionCloudIE,
) )
from .dailymail import DailyMailIE
from .onionstudios import OnionStudiosIE from .onionstudios import OnionStudiosIE
from .viewlift import ViewLiftEmbedIE from .viewlift import ViewLiftEmbedIE
from .mtv import MTVServicesEmbeddedIE from .mtv import MTVServicesEmbeddedIE
@ -760,6 +761,20 @@ class GenericIE(InfoExtractor):
}, },
'add_ie': ['Dailymotion'], 'add_ie': ['Dailymotion'],
}, },
# DailyMail embed
{
'url': 'http://www.bumm.sk/krimi/2017/07/05/biztonsagi-kamera-buktatta-le-az-agg-ferfit-utlegelo-apolot',
'info_dict': {
'id': '1495629',
'ext': 'mp4',
'title': 'Care worker punches elderly dementia patient in head 11 times',
'description': 'md5:3a743dee84e57e48ec68bf67113199a5',
},
'add_ie': ['DailyMail'],
'params': {
'skip_download': True,
},
},
# YouTube embed # YouTube embed
{ {
'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html', 'url': 'http://www.badzine.de/ansicht/datum/2014/06/09/so-funktioniert-die-neue-englische-badminton-liga.html',
@ -2190,6 +2205,12 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches( return self.playlist_from_matches(
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p) playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
# Look for DailyMail embeds
dailymail_urls = DailyMailIE._extract_urls(webpage)
if dailymail_urls:
return self.playlist_from_matches(
dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
# Look for embedded Wistia player # Look for embedded Wistia player
wistia_url = WistiaIE._extract_url(webpage) wistia_url = WistiaIE._extract_url(webpage)
if wistia_url: if wistia_url: