]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/heise.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
5 from .youtube
import YoutubeIE
14 class HeiseIE(InfoExtractor
):
15 _VALID_URL
= r
'https?://(?:www\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P<id>[0-9]+)\.html'
17 'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html',
18 'md5': 'ffed432483e922e88545ad9f2f15d30e',
22 'title': "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone",
23 'format_id': 'mp4_720p',
24 'timestamp': 1411812600,
25 'upload_date': '20140927',
26 'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
27 'thumbnail': r
're:^https?://.*/gallery/$',
31 'url': 'http://www.heise.de/newsticker/meldung/Netflix-In-20-Jahren-vom-Videoverleih-zum-TV-Revolutionaer-3814130.html',
32 'md5': 'e403d2b43fea8e405e88e3f8623909f1',
36 'title': 'NEU IM SEPTEMBER | Netflix',
37 'description': 'md5:2131f3c7525e540d5fd841de938bd452',
38 'upload_date': '20170830',
39 'uploader': 'Netflix Deutschland, Österreich und Schweiz',
40 'uploader_id': 'netflixdach',
43 'skip_download': True,
46 'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
47 'only_matching': True,
49 'url': 'http://www.heise.de/newsticker/meldung/c-t-uplink-Owncloud-Tastaturen-Peilsender-Smartphone-2404251.html?wt_mc=rss.ho.beitrag.atom',
50 'only_matching': True,
52 'url': 'http://www.heise.de/ct/ausgabe/2016-12-Spiele-3214137.html',
53 'only_matching': True,
56 def _real_extract(self
, url
):
57 video_id
= self
._match
_id
(url
)
58 webpage
= self
._download
_webpage
(url
, video_id
)
60 title
= self
._html
_search
_meta
('fulltitle', webpage
, default
=None)
61 if not title
or title
== "c't":
62 title
= self
._search
_regex
(
63 r
'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
66 yt_urls
= YoutubeIE
._extract
_urls
(webpage
)
68 return self
.playlist_from_matches(yt_urls
, video_id
, title
, ie
=YoutubeIE
.ie_key())
70 container_id
= self
._search
_regex
(
71 r
'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
72 webpage
, 'container ID')
73 sequenz_id
= self
._search
_regex
(
74 r
'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
75 webpage
, 'sequenz ID')
77 doc
= self
._download
_xml
(
78 'http://www.heise.de/videout/feed', video_id
, query
={
79 'container': container_id
,
80 'sequenz': sequenz_id
,
84 for source_node
in doc
.findall('.//{http://rss.jwpcdn.com/}source'):
85 label
= source_node
.attrib
['label']
86 height
= int_or_none(self
._search
_regex
(
87 r
'^(.*?_)?([0-9]+)p$', label
, 'height', default
=None))
88 video_url
= source_node
.attrib
['file']
89 ext
= determine_ext(video_url
, '')
93 'format_id': '%s_%s' % (ext
, label
),
96 self
._sort
_formats
(formats
)
98 description
= self
._og
_search
_description
(
99 webpage
, default
=None) or self
._html
_search
_meta
(
100 'description', webpage
)
105 'description': description
,
106 'thumbnail': (xpath_text(doc
, './/{http://rss.jwpcdn.com/}image') or
107 self
._og
_search
_thumbnail
(webpage
)),
108 'timestamp': parse_iso8601(
109 self
._html
_search
_meta
('date', webpage
)),