Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-26 18:34:32 +01:00
Code Issues Releases Wiki Activity

Fixed issues from travis-ci

Browse Source
This commit is contained in:
Dennis Fink 2016-10-03 18:19:29 +02:00
parent 53ca134ca9
commit 36ce480413
1 changed files with 73 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

116
youtube_dl/extractor/rtllu.py
View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@ -22,9 +23,7 @@ class RtlluIE(InfoExtractor):
}
def _real_extract(self, url):
match = self._VALID_URL_RE.match(url)
id = match.group('id')
id = self._match_id(url)
webpage = self._download_webpage(url, id)
javascript_regex = r'<script language="Javascript">((\n*?.*?)*?)</script>'
@ -32,60 +31,91 @@ class RtlluIE(InfoExtractor):
try:
javascript_sources_regex = r'object.*\.sources = \'(?P<value>.*?)\';'
sources = json.loads(re.search(javascript_sources_regex, javascript).group('value'))
sources = self._search_regex(javascript_sources_regex, javascript, 'sources')
sources = json.loads(sources)
javascript_videoid_regex = r'object.*\.videoid = \'(?P<value>.*?)\';'
javascript_videoid = re.search(javascript_videoid_regex, javascript).group('value')
videoid_regex = r'object.*\.videoid = \'(?P<value>.*?)\';'
videoid = self._search_regex(videoid_regex, javascript, 'videoid', fatal=False, default=id)
javascript_publicdate_regex = r'object.*\.publicdate = \'(?P<value>.*?)\';'
javascript_publicdate = re.search(javascript_publicdate_regex, javascript).group('value')
publicdate_regex = r'object.*\.publicdate = \'(?P<value>.*?)\';'
publicdate = self._search_regex(publicdate_regex, javascript, 'publicdate', fatal=False)
javascript_thumbnail_regex = r'object.*\.thumbnail = \'(?P<value>.*?)\';'
javascript_thumbnail = re.search(javascript_thumbnail_regex, javascript).group('value')
thumbnail_regex = r'object.*\.thumbnail = \'(?P<value>.*?)\';'
thumbnail = self._search_regex(thumbnail_regex, javascript, 'thumbnail', fatal=False)
formats = [
{
'url': sources['rtmp']['src'],
'format': 'RTMP Stream',
'format_id': 'rtmp',
'protocol': 'rtmp',
},
formats = []
{
'url': sources['httplq']['src'],
'format': 'Low Quality',
'format_id': 'lq',
'protocol': 'http',
},
{
'url': sources['http']['src'],
'format': 'Standard Quality',
'format_id': 'sd',
'protocol': 'http',
},
{
'url': sources['httphq']['src'],
'format': 'High Quality',
'format_id': 'hq',
'protocol': 'http',
},
]
rtmp_source = sources.get('rtmp')
if rtmp_source is not None:
rtmp_url = rtmp_source.get('src')
if rtmp_url is not None:
formats.append(
{
'url': rtmp_url,
'format': 'RTMP Stream',
'format_id': 'rtmp',
'protocol': 'rtmp'
}
)
httplq_source = sources.get('httplq')
if httplq_source is not None:
httplq_url = httplq_source.get('src')
if httplq_url is not None:
formats.append(
{
'url': httplq_url,
'format': 'Low Quality',
'format_id': 'lq',
'protocol': 'http',
}
)
http_source = sources.get('http')
if http_source is not None:
http_url = http_source.get('src')
if http_url is not None:
formats.append(
{
'url': http_url,
'format': 'Standard Quality',
'format_id': 'sd',
'protocol': 'http',
}
)
httphq_source = sources.get('httphq')
if httphq_source is not None:
httphq_url = httphq_source.get('src')
if httphq_url is not None:
formats.append(
{
'url': httphq_url,
'format': 'High Quality',
'format_id': 'hq',
'protocol': 'http',
}
)
return {
'id': javascript_videoid or id,
'id': videoid,
'title': self.get_video_title(webpage, javascript),
'formats': formats,
'thumbnail': javascript_thumbnail,
'upload_date': javascript_publicdate,
'thumbnail': thumbnail,
'upload_date': publicdate,
}
except AttributeError:
javascript_mp3_regex = r'play_mp3\("object[0-9]*", "(?P<value>.*?)",'
javascript_mp3 = re.search(javascript_mp3_regex, javascript).group('value')
mp3_regex = r'play_mp3\("object[0-9]*", "(?P<value>.*?)",'
mp3_url = self._search_regex(mp3_regex, javascript, 'mp3_url')
return {
'id': id,
'title': self.get_audio_title(webpage),
'url': javascript_mp3,
'url': mp3_url,
}
def get_video_title(self, webpage, javascript):
@ -97,7 +127,7 @@ class RtlluIE(InfoExtractor):
title = title[-1]
javascript_title_regex = r'object.*\.title = \'(?P<value>.*?)\';'
javascript_title = re.search(javascript_title_regex, javascript).group('value')
javascript_title = self._search_regex(javascript_title_regex, javascript, 'javascript_title', fatal=False)
return javascript_title or title or self._og_search_title(webpage)
def get_audio_title(self, webpage):