w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[sportschau] Improve title extraction

Browse source 
The html '<title>' ends with '- sportschau.de', which shouldn't be part of the title.
This commit is contained in:
Jaime Marquínez Ferrándiz 2015-07-19 11:24:19 +02:00
parent 8b61bfd638
commit 32470bf619
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
youtube_dl/extractor/sportschau.py
View file

@ -2,6 +2,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import get_element_by_attribute
class SportschauIE(InfoExtractor): class SportschauIE(InfoExtractor):
@ -12,7 +13,7 @@ class SportschauIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100', 'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun" - Tour de France - sportschau.de', 'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.', 'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.',
}, },
@ -34,7 +35,7 @@ class SportschauIE(InfoExtractor):
m3u8_formats = self._extract_m3u8_formats(m3u8_url, video_id, ext="mp4") m3u8_formats = self._extract_m3u8_formats(m3u8_url, video_id, ext="mp4")
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') title = get_element_by_attribute('class', 'headline', webpage)
desc = self._html_search_meta('description', webpage) desc = self._html_search_meta('description', webpage)
return { return {