Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-03 06:12:57 +08:00
Code Issues Releases Wiki Activity

Fix for Heise extractor

Browse Source
This commit is contained in:
Hier631 2017-12-15 19:11:44 +01:00 committed by GitHub
parent 498a8a4ca5
commit e0bb97aba7
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
youtube_dl/extractor/heise.py
View File

@ -12,7 +12,7 @@ from ..utils import (
class HeiseIE(InfoExtractor): class HeiseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P<id>[0-9]+)\.html' _VALID_URL = r'https?://(?:www\.|m\.)?heise\.de/(?:[^/]+/)+[^/]+-(?P<id>[0-9]+)\.html'
_TESTS = [{ _TESTS = [{
'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html', 'url': 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html',
'md5': 'ffed432483e922e88545ad9f2f15d30e', 'md5': 'ffed432483e922e88545ad9f2f15d30e',
@ -54,6 +54,7 @@ class HeiseIE(InfoExtractor):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
url = url.replace('www', 'm', 1)
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)
@ -97,7 +98,7 @@ class HeiseIE(InfoExtractor):
description = self._og_search_description( description = self._og_search_description(
webpage, default=None) or self._html_search_meta( webpage, default=None) or self._html_search_meta(
'description', webpage) 'description', webpage, default=None)
return { return {
'id': video_id, 'id': video_id,
@ -106,6 +107,6 @@ class HeiseIE(InfoExtractor):
'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image') or 'thumbnail': (xpath_text(doc, './/{http://rss.jwpcdn.com/}image') or
self._og_search_thumbnail(webpage)), self._og_search_thumbnail(webpage)),
'timestamp': parse_iso8601( 'timestamp': parse_iso8601(
self._html_search_meta('date', webpage)), self._html_search_meta('date', webpage, default=None)),
'formats': formats, 'formats': formats,
} }