Archives/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 15:25:49 +00:00
Code Issues Projects Releases Wiki Activity

[extremetube] Fix extraction (Closes #5127)

Browse Source
This commit is contained in:
Naglis Jonaitis 2015-03-05 14:45:38 +02:00
parent 12a129ec6d
commit c2ebea6580
1 changed files with 19 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
youtube_dl/extractor/extremetube.py
View File

@ -4,11 +4,11 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse_urlparse, compat_parse_qs,
compat_urllib_request, compat_urllib_request,
compat_urllib_parse,
) )
from ..utils import ( from ..utils import (
qualities,
str_to_int, str_to_int,
) )
@ -17,7 +17,7 @@ class ExtremeTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)' _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'md5': '1fb9228f5e3332ec8c057d6ac36f33e0', 'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
'info_dict': { 'info_dict': {
'id': '652431', 'id': '652431',
'ext': 'mp4', 'ext': 'mp4',
@ -49,19 +49,27 @@ def _real_extract(self, url):
r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>', r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
video_url = compat_urllib_parse.unquote(self._html_search_regex( flash_vars = compat_parse_qs(self._search_regex(
r'video_url=(.+?)&amp;', webpage, 'video_url')) r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
path = compat_urllib_parse_urlparse(video_url).path
format = path.split('/')[5].split('_')[:2] formats = []
format = "-".join(format) quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
for k, vals in flash_vars.items():
m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
if m is not None:
formats.append({
'format_id': m.group('quality'),
'quality': quality(m.group('quality')),
'url': vals[0],
})
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': video_title, 'title': video_title,
'formats': formats,
'uploader': uploader, 'uploader': uploader,
'view_count': view_count, 'view_count': view_count,
'url': video_url,
'format': format,
'format_id': format,
'age_limit': 18, 'age_limit': 18,
} }