yt-dlp/youtube_dl/extractor/heise.py

132 lines
4.9 KiB
Python
Raw Normal View History

2014-09-27 17:28:01 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from .kaltura import KalturaIE
2017-09-17 15:46:52 +00:00
from .youtube import YoutubeIE
2014-09-27 17:28:01 +00:00
from ..utils import (
determine_ext,
int_or_none,
2014-09-27 17:28:01 +00:00
parse_iso8601,
smuggle_url,
2017-02-17 16:09:40 +00:00
xpath_text,
2014-09-27 17:28:01 +00:00
)
class HeiseIE(InfoExtractor):
2017-02-17 16:09:40 +00:00
_VALID_URL = r'https?://(?:www\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P<id>[0-9]+)\.html'
_TESTS = [{
'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html',
'md5': 'ffed432483e922e88545ad9f2f15d30e',
'info_dict': {
'id': '2404147',
'ext': 'mp4',
'title': "Podcast: c't uplink 3.3 Owncloud / Tastaturen / Peilsender Smartphone",
'format_id': 'mp4_720p',
'timestamp': 1411812600,
'upload_date': '20140927',
'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
'thumbnail': r're:^https?://.*/gallery/$',
}
2017-09-17 15:46:52 +00:00
}, {
# YouTube embed
'url': 'http://www.heise.de/newsticker/meldung/Netflix-In-20-Jahren-vom-Videoverleih-zum-TV-Revolutionaer-3814130.html',
'md5': 'e403d2b43fea8e405e88e3f8623909f1',
'info_dict': {
'id': '6kmWbXleKW4',
'ext': 'mp4',
'title': 'NEU IM SEPTEMBER | Netflix',
'description': 'md5:2131f3c7525e540d5fd841de938bd452',
'upload_date': '20170830',
'uploader': 'Netflix Deutschland, Österreich und Schweiz',
'uploader_id': 'netflixdach',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.heise.de/video/artikel/nachgehakt-Wie-sichert-das-c-t-Tool-Restric-tor-Windows-10-ab-3700244.html',
'md5': '4b58058b46625bdbd841fc2804df95fc',
'info_dict': {
'id': '1_ntrmio2s',
'timestamp': 1512470717,
'upload_date': '20171205',
'ext': 'mp4',
'title': 'ct10 nachgehakt hos restrictor',
},
'params': {
'skip_download': True,
},
2017-02-17 16:09:40 +00:00
}, {
'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
'only_matching': True,
}, {
'url': 'http://www.heise.de/newsticker/meldung/c-t-uplink-Owncloud-Tastaturen-Peilsender-Smartphone-2404251.html?wt_mc=rss.ho.beitrag.atom',
'only_matching': True,
}, {
'url': 'http://www.heise.de/ct/ausgabe/2016-12-Spiele-3214137.html',
'only_matching': True,
}]
2014-09-27 17:28:01 +00:00
def _real_extract(self, url):
2014-09-28 08:40:49 +00:00
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2017-09-17 15:46:52 +00:00
title = self._html_search_meta('fulltitle', webpage, default=None)
if not title or title == "c't":
title = self._search_regex(
2017-09-23 00:26:40 +00:00
r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
webpage, 'title')
2017-09-17 15:46:52 +00:00
yt_urls = YoutubeIE._extract_urls(webpage)
if yt_urls:
return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key())
kaltura_url = KalturaIE._extract_url(webpage)
if kaltura_url:
return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
container_id = self._search_regex(
2017-02-17 16:09:40 +00:00
r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
webpage, 'container ID')
sequenz_id = self._search_regex(
2017-02-17 16:09:40 +00:00
r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
webpage, 'sequenz ID')
2014-09-27 17:28:01 +00:00
2017-02-17 16:09:40 +00:00
doc = self._download_xml(
'http://www.heise.de/videout/feed', video_id, query={
'container': container_id,
'sequenz': sequenz_id,
})
2014-09-27 17:28:01 +00:00
formats = []
for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'):
label = source_node.attrib['label']
height = int_or_none(self._search_regex(
r'^(.*?_)?([0-9]+)p$', label, 'height', default=None))
video_url = source_node.attrib['file']
ext = determine_ext(video_url, '')
formats.append({
'url': video_url,
'format_note': label,
'format_id': '%s_%s' % (ext, label),
'height': height,
})
2014-09-27 17:28:01 +00:00
self._sort_formats(formats)
2017-02-17 16:09:40 +00:00
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'description', webpage)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image') or
self._og_search_thumbnail(webpage)),
'timestamp': parse_iso8601(
self._html_search_meta('date', webpage)),
'formats': formats,
}