aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--youtube_dl/extractor/unistra.py88
1 files changed, 55 insertions, 33 deletions
diff --git a/youtube_dl/extractor/unistra.py b/youtube_dl/extractor/unistra.py
index bd5a258a5..f70978299 100644
--- a/youtube_dl/extractor/unistra.py
+++ b/youtube_dl/extractor/unistra.py
@@ -1,44 +1,66 @@
+from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
+from ..utils import qualities
+
class UnistraIE(InfoExtractor):
- _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(\d+)'
-
- _TEST = {
- u'url': u'http://utv.unistra.fr/video.php?id_video=154',
- u'file': u'154.mp4',
- u'md5': u'736f605cfdc96724d55bb543ab3ced24',
- u'info_dict': {
- u'title': u'M!ss Yella',
- u'description': u'md5:104892c71bd48e55d70b902736b81bbf',
+ _VALID_URL = r'http://utv\.unistra\.fr/(?:index|video)\.php\?id_video\=(?P<id>\d+)'
+
+ _TESTS = [
+ {
+ 'url': 'http://utv.unistra.fr/video.php?id_video=154',
+ 'md5': '736f605cfdc96724d55bb543ab3ced24',
+ 'info_dict': {
+ 'id': '154',
+ 'ext': 'mp4',
+ 'title': 'M!ss Yella',
+ 'description': 'md5:104892c71bd48e55d70b902736b81bbf',
+ },
},
- }
+ {
+ 'url': 'http://utv.unistra.fr/index.php?id_video=437',
+ 'md5': '1ddddd6cccaae76f622ce29b8779636d',
+ 'info_dict': {
+ 'id': '437',
+ 'ext': 'mp4',
+ 'title': 'Prix Louise Weiss 2014',
+ 'description': 'md5:cc3a8735f079f4fb6b0b570fc10c135a',
+ },
+ }
+ ]
def _real_extract(self, url):
- video_id = re.match(self._VALID_URL, url).group(1)
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+
webpage = self._download_webpage(url, video_id)
- width = re.search(r'width: "(\d*?)",', webpage).group(1)
- height = re.search(r'height: "(\d*?)",', webpage).group(1)
- files = re.findall(r'file: "(.*?)"', webpage)
- video_url = 'http://vod-flash.u-strasbg.fr:8080'
- formats = [{
- 'format_id': 'SD',
- 'url': video_url + files[0],
- 'ext': 'mp4',
- 'resolution': width + 'x' + height
- }]
- if files[1] != files[0]:
+
+ files = set(re.findall(r'file\s*:\s*"([^"]+)"', webpage))
+
+ quality = qualities(['SD', 'HD'])
+ formats = []
+ for file_path in files:
+ format_id = 'HD' if file_path.endswith('-HD.mp4') else 'SD'
formats.append({
- 'format_id': 'HD',
- 'url': video_url + files[1],
- 'ext': 'mp4'
+ 'url': 'http://vod-flash.u-strasbg.fr:8080%s' % file_path,
+ 'format_id': format_id,
+ 'quality': quality(format_id)
})
- title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title')
-
- return {'id': video_id,
- 'title': title,
- 'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL),
- 'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'),
- 'formats': formats
- }
+
+ title = self._html_search_regex(
+ r'<title>UTV - (.*?)</', webpage, 'title')
+ description = self._html_search_regex(
+ r'<meta name="Description" content="(.*?)"', webpage, 'description', flags=re.DOTALL)
+ thumbnail = self._search_regex(
+ r'image: "(.*?)"', webpage, 'thumbnail')
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'formats': formats
+ }