aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-10-26 23:11:15 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2014-10-26 23:11:15 +0100
commit526b276fd7199414d199f2913bc794677d0933ac (patch)
tree0227b15b7f9ce62874f3f1a3a28978fc450da366
parent77ec444d9a20fb0e3aa1be2941979189d53ebdb3 (diff)
[faz] Modernize
-rw-r--r--youtube_dl/extractor/faz.py36
1 files changed, 19 insertions, 17 deletions
diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py
index c6ab6952e..f3d45b2be 100644
--- a/youtube_dl/extractor/faz.py
+++ b/youtube_dl/extractor/faz.py
@@ -1,5 +1,5 @@
# encoding: utf-8
-import re
+from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
@@ -8,42 +8,44 @@ from ..utils import (
class FazIE(InfoExtractor):
- IE_NAME = u'faz.net'
+ IE_NAME = 'faz.net'
_VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html'
_TEST = {
- u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
- u'file': u'12610585.mp4',
- u'info_dict': {
- u'title': u'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
- u'description': u'md5:1453fbf9a0d041d985a47306192ea253',
+ 'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html',
+ 'info_dict': {
+ 'id': '12610585',
+ 'ext': 'mp4',
+ 'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher',
+ 'description': 'md5:1453fbf9a0d041d985a47306192ea253',
},
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- self.to_screen(video_id)
+ video_id = self._match_id(url)
+
webpage = self._download_webpage(url, video_id)
- config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage,
- u'config xml url')
- config = self._download_xml(config_xml_url, video_id,
- u'Downloading config xml')
+ config_xml_url = self._search_regex(
+ r'writeFLV\(\'(.+?)\',', webpage, 'config xml url')
+ config = self._download_xml(
+ config_xml_url, video_id, 'Downloading config xml')
encodings = config.find('ENCODINGS')
formats = []
- for code in ['LOW', 'HIGH', 'HQ']:
+ for pref, code in enumerate(['LOW', 'HIGH', 'HQ']):
encoding = encodings.find(code)
if encoding is None:
continue
encoding_url = encoding.find('FILENAME').text
formats.append({
'url': encoding_url,
- 'ext': determine_ext(encoding_url),
'format_id': code.lower(),
+ 'quality': pref,
})
+ self._sort_formats(formats)
- descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description')
+ descr = self._html_search_regex(
+ r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False)
return {
'id': video_id,
'title': self._og_search_title(webpage),