github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[phoenix] Add new extractor (Fixes #4036)

Browse source
This commit is contained in:
Philipp Hagemeister 2014-10-27 02:43:59 +01:00
parent b0fb6d4db1
commit 8cc3eba79a
3 changed files with 109 additions and 74 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
youtube_dl/extractor/__init__.py
View file

@ -280,6 +280,7 @@
from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
from .pbs import PBSIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .planetaplay import PlanetaPlayIE
from .played import PlayedIE

31
youtube_dl/extractor/phoenix.py Normal file
View file

@ -0,0 +1,31 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .zdf import extract_from_xml_url
class PhoenixIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?phoenix\.de/content/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.phoenix.de/content/884301',
'md5': 'ed249f045256150c92e72dbb70eadec6',
'info_dict': {
'id': '884301',
'ext': 'mp4',
'title': 'Michael Krons mit Hans-Werner Sinn',
'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
'upload_date': '20141025',
'uploader': 'Im Dialog',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
internal_id = self._search_regex(
r'<div class="phx_vod" id="phx_vod_([0-9]+)"',
webpage, 'internal video ID')
api_url = 'http://www.phoenix.de/php/zdfplayer-v1.3/data/beitragsDetails.php?ak=web&id=%s' % internal_id
return extract_from_xml_url(self, video_id, api_url)

53
youtube_dl/extractor/zdf.py
View file

@ -10,29 +10,8 @@
)
class ZDFIE(InfoExtractor):
_VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
_TEST = {
'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
'info_dict': {
'id': '2037704',
'ext': 'webm',
'title': 'ZDFspezial - Ende des Machtpokers',
'description': 'Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial "Ende des Machtpokers - Große Koalition für Deutschland".',
'duration': 1022,
'uploader': 'spezial',
'uploader_id': '225948',
'upload_date': '20131127',
},
'skip': 'Videos on ZDF.de are depublicised in short order',
}
def _real_extract(self, url):
video_id = self._match_id(url)
xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
doc = self._download_xml(
def extract_from_xml_url(ie, video_id, xml_url):
doc = ie._download_xml(
xml_url, video_id,
note='Downloading video info',
errnote='Failed to download video info')
@ -93,8 +72,7 @@ def xml_to_format(fnode):
formats = list(filter(
lambda f: f['_available'],
map(xml_to_format, format_nodes)))
self._sort_formats(formats)
ie._sort_formats(formats)
return {
'id': video_id,
@ -106,3 +84,28 @@ def xml_to_format(fnode):
'upload_date': upload_date,
'formats': formats,
}
class ZDFIE(InfoExtractor):
_VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?'
_TEST = {
'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt',
'info_dict': {
'id': '2037704',
'ext': 'webm',
'title': 'ZDFspezial - Ende des Machtpokers',
'description': 'Union und SPD haben sich auf einen Koalitionsvertrag geeinigt. Aber was bedeutet das für die Bürger? Sehen Sie hierzu das ZDFspezial "Ende des Machtpokers - Große Koalition für Deutschland".',
'duration': 1022,
'uploader': 'spezial',
'uploader_id': '225948',
'upload_date': '20131127',
},
'skip': 'Videos on ZDF.de are depublicised in short order',
}
def _real_extract(self, url):
video_id = self._match_id(url)
xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
return extract_from_xml_url(self, video_id, xml_url)