Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-13 11:50:00 +08:00
Code Issues Releases Wiki Activity

[Joj] * fixed broken compatibility with Python 2.6

Browse Source 
[Joj] * removed debug output
[Joj] * removed parsing unimportant title_query
[Joj] * fixed sorting formats
This commit is contained in:
luboss 2017-07-03 20:58:35 +02:00
parent 5f65d99ea2
commit f6cff4b6f0
1 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
youtube_dl/extractor/joj.py
View File

@ -6,7 +6,7 @@ import re
class JojIE(InfoExtractor):
_VALID_URL = r'https?://([a-z0-9]+\.)joj\.sk/([^/]+/)*(?P<title_query>(?P<release_date>[0-9]{4}(-[0-9]{2}){2}).*)' # noqa
_VALID_URL = r'https?://[a-z0-9]+\.joj\.sk/([^/]+/)*(?P<title_query>(?P<release_date>[0-9]{4}(-[0-9]{2}){2}).*)' # noqa
_TESTS = [{
'url': 'https://www.joj.sk/nove-byvanie/archiv/2017-05-28-nove-byvanie', # noqa
'info_dict': {
@ -30,27 +30,27 @@ class JojIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title_query = mobj.group('title_query')
release_date = mobj.group('release_date').replace('-', '')
webpage = self._download_webpage(url, 'video_id')
webpage = self._download_webpage(url, 'id')
video_id = self._html_search_regex(
r'https?://([a-z0-9]+\.)joj\.sk/embed/(?P<video_id>[a-f0-9\-]+)', webpage,
'id', group='video_id', default=None)
print(video_id)
r'https?://([a-z0-9]+\.)joj\.sk/embed/(?P<video_id>[a-f0-9\-]+)',
webpage, 'id', group='video_id')
xml_playlist_url = self.xml_source_url + video_id
xml_playlist_et = self._download_xml(xml_playlist_url, title_query)
xml_playlist_et = self._download_xml(xml_playlist_url, 'XML playlist')
formats = []
for file_el in xml_playlist_et.iter('file'):
formats.append({'height': file_el.attrib['id'].replace('p', ''),
for file_el in xml_playlist_et.findall('files/file'):
try:
height = int(file_el.attrib['id'].replace('p', ''))
except ValueError:
height = 0
formats.append({'height': height,
'url': self.media_src_url + file_el.attrib['path'].replace( # noqa
'dat/', '', 1)})
def get_height(d):
return d.get('height')
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage).title(),
'formats': sorted(formats, key=get_height),
'formats': formats,
'release_date': release_date
}