diff options
| author | Remita Amine <remitamine@gmail.com> | 2017-04-02 00:26:48 +0100 |
|---|---|---|
| committer | Remita Amine <remitamine@gmail.com> | 2017-04-02 00:26:48 +0100 |
| commit | dbf70c489f1bcf36d44afb8384d7abdb8a34d960 (patch) | |
| tree | 7de9e81b5b7089c5329d26fe627259fa4aefb70b /youtube_dl/extractor | |
| parent | 61e2331ad83569b3256e32f415c22cc439c000ed (diff) | |
[tv5mondeplus] clean description and use stable id
Diffstat (limited to 'youtube_dl/extractor')
| -rw-r--r-- | youtube_dl/extractor/tv5mondeplus.py | 9 |
1 files changed, 5 insertions, 4 deletions
diff --git a/youtube_dl/extractor/tv5mondeplus.py b/youtube_dl/extractor/tv5mondeplus.py index 8b2d7812a..88b6baa31 100644 --- a/youtube_dl/extractor/tv5mondeplus.py +++ b/youtube_dl/extractor/tv5mondeplus.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( + clean_html, determine_ext, extract_attributes, get_element_by_class, @@ -19,10 +20,10 @@ class TV5MondePlusIE(InfoExtractor): 'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', 'md5': '12130fc199f020673138a83466542ec6', 'info_dict': { - 'id': '0a774110-dc60-4037-f769-996439514f1f', + 'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants', 'ext': 'mp4', 'title': 'Tdah, mon amour - Enfants', - 'description': 'md5:b65f0cc50e46947e62e5d352e9916cc4', + 'description': 'md5:230e3aca23115afcf8006d1bece6df74', 'upload_date': '20170401', 'timestamp': 1491022860, } @@ -65,10 +66,10 @@ class TV5MondePlusIE(InfoExtractor): self._sort_formats(formats) return { - 'id': vpl_data.get('data-guid') or display_id, + 'id': display_id, 'display_id': display_id, 'title': title, - 'description': get_element_by_class('video-detail__description', webpage), + 'description': clean_html(get_element_by_class('video-detail__description', webpage)), 'thumbnail': vpl_data.get('data-image'), 'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)), 'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)), |