diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2015-07-19 11:24:19 +0200 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2015-07-19 11:27:12 +0200 |
| commit | 32470bf619d31605dc9c51ad107839a097f829f4 (patch) | |
| tree | e62c08b669bf0bc6eea7263d1fa28ce0afd737f0 /youtube_dl/extractor/sportschau.py | |
| parent | 8b61bfd6389b62f054cdf9dcb3436395c82a8e28 (diff) | |
| download | youtube-dl-32470bf619d31605dc9c51ad107839a097f829f4.zip youtube-dl-32470bf619d31605dc9c51ad107839a097f829f4.tar.gz youtube-dl-32470bf619d31605dc9c51ad107839a097f829f4.tar.bz2 | |
[sportschau] Improve title extraction
The html '<title>' ends with '- sportschau.de', which shouldn't be part of the title.
Diffstat (limited to 'youtube_dl/extractor/sportschau.py')
| -rw-r--r-- | youtube_dl/extractor/sportschau.py | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/youtube_dl/extractor/sportschau.py b/youtube_dl/extractor/sportschau.py index 2879726..bf9b075 100644 --- a/youtube_dl/extractor/sportschau.py +++ b/youtube_dl/extractor/sportschau.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import get_element_by_attribute class SportschauIE(InfoExtractor): @@ -12,7 +13,7 @@ class SportschauIE(InfoExtractor): 'info_dict': { 'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100', '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$', '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") 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) return { |