[heise] Improve (closes #9725)

This commit is contained in:
Sergey M․ 2017-02-17 23:09:40 +07:00
parent db76c30c6e
commit bad4ccdb5d
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 48 additions and 98 deletions

View File

@ -6,120 +6,58 @@ from ..utils import (
determine_ext, determine_ext,
int_or_none, int_or_none,
parse_iso8601, parse_iso8601,
xpath_text,
) )
class HeiseIE(InfoExtractor): class HeiseIE(InfoExtractor):
_VALID_URL = r'''(?x) _VALID_URL = r'https?://(?:www\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P<id>[0-9]+)\.html'
https?://(?:www\.)?heise\.de/.+?(?P<id>[0-9]+)\.html(?:$|[?#]) _TESTS = [{
''' 'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html',
_TESTS = [ 'md5': 'ffed432483e922e88545ad9f2f15d30e',
{ 'info_dict': {
'url': ( 'id': '2404147',
'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html' 'ext': 'mp4',
), 'title': "Podcast: c't uplink 3.3 Owncloud / Tastaturen / Peilsender Smartphone",
'md5': 'ffed432483e922e88545ad9f2f15d30e', 'format_id': 'mp4_720p',
'info_dict': { 'timestamp': 1411812600,
'id': '2404147', 'upload_date': '20140927',
'ext': 'mp4', 'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
'title': ( 'thumbnail': r're:^https?://.*/gallery/$',
"Podcast: c't uplink 3.3 Owncloud / Tastaturen / Peilsender Smartphone" }
), }, {
'format_id': 'mp4_720p', 'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
'timestamp': 1411812600, 'only_matching': True,
'upload_date': '20140927', }, {
'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.', 'url': 'http://www.heise.de/newsticker/meldung/c-t-uplink-Owncloud-Tastaturen-Peilsender-Smartphone-2404251.html?wt_mc=rss.ho.beitrag.atom',
'thumbnail': r're:^https?://.*/gallery/$', 'only_matching': True,
} }, {
}, 'url': 'http://www.heise.de/ct/ausgabe/2016-12-Spiele-3214137.html',
{ 'only_matching': True,
'url': ( }]
'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html'
),
'md5': 'ffed432483e922e88545ad9f2f15d30e',
'info_dict': {
'id': '2403911',
'ext': 'mp4',
'title': (
"c't uplink 3.3: Owncloud, Tastaturen, Peilsender Smartphone"
),
'format_id': 'mp4_720p',
'timestamp': 1411803000,
'upload_date': '20140927',
'description': "In c't uplink erklären wir in dieser Woche, wie man mit Owncloud die Kontrolle über die eigenen Daten behält. Darüber hinaus erklären wir, dass zur Wahl der richtigen Tastatur mehr gehört, als man denkt und wie Smartphones uns weiter verraten.",
'thumbnail': r're:^https?://.*/gallery/$',
}
},
{
'url': (
'http://www.heise.de/newsticker/meldung/c-t-uplink-Owncloud-Tastaturen-Peilsender-Smartphone-2404251.html?wt_mc=rss.ho.beitrag.atom'
),
'md5': 'ffed432483e922e88545ad9f2f15d30e',
'info_dict': {
'id': '2404251',
'ext': 'mp4',
'title': (
"c't uplink: Owncloud, Tastaturen, Peilsender Smartphone"
),
'format_id': 'mp4_720p',
'timestamp': 1411811400,
'upload_date': '20140927',
'description': 'In uplink-Episode 3.3 sprechen wir über Owncloud und wie man sich damit von Cloudanbietern emanzipieren kann. Außerdem erklären wir, woran man alles beim Kauf einer Tastatur denken sollte und was Smartphones nun über uns verraten.',
'thumbnail': r're:^https?://.*/gallery/$',
}
},
{
'url': (
'http://www.heise.de/ct/ausgabe/2016-12-Spiele-3214137.html'
),
'md5': '0616c9297d9c989f9b2a23b483b408c3',
'info_dict': {
'id': '3214137',
'ext': 'mp4',
'title': (
"c\u2019t zockt \u201eGlitchspace\u201c, \u201eThe Mind's Eclipse\u201c und \u201eWindowframe\u201c."
),
'format_id': 'mp4_720p',
'timestamp': 1464011220,
'upload_date': '20160523',
'description': "Unsere Spiele-Tipps der Woche: Das Puzzle-Adventure Glitchspace, das Jump&Run-Spiel Windowframe und The Mind's Eclipse",
'thumbnail': r're:^https?://.*/gallery/$',
}
},
]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
container_id = self._search_regex( container_id = self._search_regex(
r'<div class="videoplayerjw"[^>]*data-container="([0-9]+)"', r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
webpage, 'container ID') webpage, 'container ID')
sequenz_id = self._search_regex( sequenz_id = self._search_regex(
r'<div class="videoplayerjw"[^>]*data-sequenz="([0-9]+)"', r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
webpage, 'sequenz ID') webpage, 'sequenz ID')
data_url = 'http://www.heise.de/videout/feed?container=%s&sequenz=%s' % (container_id, sequenz_id)
doc = self._download_xml(data_url, video_id)
info = {
'id': video_id,
'thumbnail': doc.find('.//{http://rss.jwpcdn.com/}image').text,
'timestamp': parse_iso8601(
self._html_search_meta('date', webpage))
}
title = self._html_search_meta('fulltitle', webpage, default=None) title = self._html_search_meta('fulltitle', webpage, default=None)
if not title or title == "c't": if not title or title == "c't":
title = self._search_regex( title = self._search_regex(
r'<div class="videoplayerjw"[^>]*data-title="([^"]+)"', r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
webpage, 'video title') webpage, 'title')
info['title'] = title
desc = self._og_search_description(webpage, default=None) doc = self._download_xml(
if not desc: 'http://www.heise.de/videout/feed', video_id, query={
desc = self._html_search_meta('description', webpage) 'container': container_id,
info['description'] = desc 'sequenz': sequenz_id,
})
formats = [] formats = []
for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'): for source_node in doc.findall('.//{http://rss.jwpcdn.com/}source'):
@ -135,6 +73,18 @@ class HeiseIE(InfoExtractor):
'height': height, 'height': height,
}) })
self._sort_formats(formats) self._sort_formats(formats)
info['formats'] = formats
return info 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,
}