aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2014-09-19 20:58:50 +0700
committerSergey M <dstftw@gmail.com>2014-09-19 20:58:50 +0700
commit532f5bff70cc32f54f38fbce9233a88faf4423b9 (patch)
tree44ecfea360542b6522654a7a44564242400cd364
parentf566d9f1d54a61497a17c5ed62a32ee1387483bd (diff)
downloadyoutube-dl-532f5bff70cc32f54f38fbce9233a88faf4423b9.tar.xz
[franceinter] Fix extraction and modernize
-rw-r--r--youtube_dl/extractor/franceinter.py28
1 files changed, 21 insertions, 7 deletions
diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py
index deb1b0b9d..6613ee17a 100644
--- a/youtube_dl/extractor/franceinter.py
+++ b/youtube_dl/extractor/franceinter.py
@@ -4,16 +4,21 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..utils import int_or_none
class FranceInterIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})'
+ _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.franceinter.fr/player/reecouter?play=793962',
- 'file': '793962.mp3',
'md5': '4764932e466e6f6c79c317d2e74f6884',
"info_dict": {
- "title": "L’Histoire dans les jeux vidéo",
+ 'id': '793962',
+ 'ext': 'mp3',
+ 'title': 'L’Histoire dans les jeux vidéo',
+ 'description': 'md5:7e93ddb4451e7530022792240a3049c7',
+ 'timestamp': 1387369800,
+ 'upload_date': '20131218',
},
}
@@ -22,17 +27,26 @@ class FranceInterIE(InfoExtractor):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
- title = self._html_search_regex(
- r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title')
+
path = self._search_regex(
- r'&urlAOD=(.*?)&startTime', webpage, 'video url')
+ r'<a id="player".+?href="([^"]+)"', webpage, 'video url')
video_url = 'http://www.franceinter.fr/' + path
+ title = self._html_search_regex(
+ r'<span class="title">(.+?)</span>', webpage, 'title')
+ description = self._html_search_regex(
+ r'<span class="description">(.*?)</span>',
+ webpage, 'description', fatal=False)
+ timestamp = int_or_none(self._search_regex(
+ r'data-date="(\d+)"', webpage, 'upload date', fatal=False))
+
return {
'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'timestamp': timestamp,
'formats': [{
'url': video_url,
'vcodec': 'none',
}],
- 'title': title,
}