Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-13 21:34:31 +01:00
Code Issues Releases Wiki Activity

[bigflix] Improve formats extraction

Browse Source
This commit is contained in:
Sergey M․ 2016-01-10 10:49:27 +06:00
parent 6e99d5762a
commit a9bbd26f1d
1 changed files with 28 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
youtube_dl/extractor/bigflix.py
View File

@ -20,7 +20,7 @@ class BigflixIE(InfoExtractor):
'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d',
}
}, {
# multiple formats
# 2 formats
'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
'info_dict': {
'id': '16070',
@ -32,6 +32,10 @@ class BigflixIE(InfoExtractor):
'params': {
'skip_download': True,
}
}, {
# multiple formats
'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
'only_matching': True,
}]
def _real_extract(self, url):
@ -45,20 +49,31 @@ class BigflixIE(InfoExtractor):
def decode_url(quoted_b64_url):
return base64.b64decode(compat_urllib_parse_unquote(
quoted_b64_url)).encode('ascii').decode('utf-8')
quoted_b64_url).encode('ascii')).decode('utf-8')
formats = [{
'url': decode_url(encoded_url),
'format_id': '%sp' % height,
'height': int(height),
} for height, encoded_url in re.findall(
r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage)]
formats = []
for height, encoded_url in re.findall(
r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
video_url = decode_url(encoded_url)
f = {
'url': video_url,
'format_id': '%sp' % height,
'height': int(height),
}
if video_url.startswith('rtmp'):
f['ext'] = 'flv'
formats.append(f)
if not formats:
formats.append({
'url': decode_url(self._search_regex(
r'file=([^&]+)', webpage, 'video url')),
})
file_url = self._search_regex(
r'file=([^&]+)', webpage, 'video url', default=None)
if file_url:
video_url = decode_url(file_url)
if all(f['url'] != video_url for f in formats):
formats.append({
'url': decode_url(file_url),
})
self._sort_formats(formats)
description = self._html_search_meta('description', webpage)