w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[dfb] Extract display_id and modernize

Browse source
This commit is contained in:
Sergey M․ 2015-07-14 23:59:21 +06:00
parent eae89f92e6
commit ddcdc684e2
1 changed files with 10 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
youtube_dl/extractor/dfb.py
View file

@ -3,17 +3,19 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import unified_strdate
class DFBIE(InfoExtractor): class DFBIE(InfoExtractor):
IE_NAME = 'tv.dfb.de' IE_NAME = 'tv.dfb.de'
_VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P<id>\d+)' _VALID_URL = r'https?://tv\.dfb\.de/video/(?P<display_id>[^/]+)/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://tv.dfb.de/video/u-19-em-stimmen-zum-spiel-gegen-russland/11633/', 'url': 'http://tv.dfb.de/video/u-19-em-stimmen-zum-spiel-gegen-russland/11633/',
# The md5 is different each time # The md5 is different each time
'info_dict': { 'info_dict': {
'id': '11633', 'id': '11633',
'display_id': 'u-19-em-stimmen-zum-spiel-gegen-russland',
'ext': 'flv', 'ext': 'flv',
'title': 'U 19-EM: Stimmen zum Spiel gegen Russland', 'title': 'U 19-EM: Stimmen zum Spiel gegen Russland',
'upload_date': '20150714', 'upload_date': '20150714',
@ -23,22 +25,25 @@ class DFBIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, display_id)
player_info = self._download_xml( player_info = self._download_xml(
'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id, 'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id,
video_id) display_id)
video_info = player_info.find('video') video_info = player_info.find('video')
f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id) f4m_info = self._download_xml(
self._proto_relative_url(video_info.find('url').text.strip()), display_id)
token_el = f4m_info.find('token') token_el = f4m_info.find('token')
manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0'
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'title': video_info.find('title').text, 'title': video_info.find('title').text,
'url': manifest_url, 'url': manifest_url,
'ext': 'flv', 'ext': 'flv',
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]), 'upload_date': unified_strdate(video_info.find('time_date').text),
} }