1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-15 03:27:46 +01:00
youtube-dl/youtube_dl/extractor/xtube.py

135 lines
4.5 KiB
Python
Raw Normal View History

2014-02-11 08:57:49 +01:00
from __future__ import unicode_literals
2013-10-28 19:23:48 +01:00
import re
from .common import InfoExtractor
from ..compat import (
2013-10-28 19:23:48 +01:00
compat_urllib_request,
compat_urllib_parse,
)
from ..utils import (
parse_duration,
str_to_int,
2013-10-28 19:23:48 +01:00
)
2013-10-28 19:23:48 +01:00
class XTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&#]+))'
2013-10-28 19:23:48 +01:00
_TEST = {
2014-02-11 08:57:49 +01:00
'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
'info_dict': {
'id': 'kVTUy_G222_',
'ext': 'mp4',
'title': 'strange erotica',
2015-02-18 19:58:41 +01:00
'description': 'contains:an ET kind of thing',
'uploader': 'greenshowers',
'duration': 450,
'age_limit': 18,
2013-10-28 19:23:48 +01:00
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
2013-10-28 19:23:48 +01:00
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(
r'<p class="title">([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex(
[r"var\s+contentOwnerId\s*=\s*'([^']+)",
2015-01-02 16:46:57 +01:00
r'By:\s*<a href="/community/profile\.php\?user=([^"]+)'],
webpage, 'uploader', fatal=False)
video_description = self._html_search_regex(
r'<p class="fieldsDesc">([^<]+)',
webpage, 'description', fatal=False)
duration = parse_duration(self._html_search_regex(
r'<span class="bold">Runtime:</span> ([^<]+)</p>',
webpage, 'duration', fatal=False))
view_count = str_to_int(self._html_search_regex(
r'<span class="bold">Views:</span> ([\d,\.]+)</p>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'<div id="commentBar">([\d,\.]+) Comments</div>',
webpage, 'comment count', fatal=False))
2014-03-21 17:58:40 +01:00
formats = []
for format_id, video_url in re.findall(
r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage):
fmt = {
'url': compat_urllib_parse.unquote(video_url),
2014-03-21 17:58:40 +01:00
'format_id': format_id,
}
m = re.search(r'^(?P<height>\d+)[pP]', format_id)
if m:
fmt['height'] = int(m.group('height'))
formats.append(fmt)
if not formats:
video_url = compat_urllib_parse.unquote(self._search_regex(
r'flashvars\.video_url\s*=\s*"([^"]+)"',
webpage, 'video URL'))
formats.append({'url': video_url})
2014-03-21 17:58:40 +01:00
self._sort_formats(formats)
2013-10-28 19:23:48 +01:00
return {
'id': video_id,
'title': video_title,
'uploader': video_uploader,
'description': video_description,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
2014-03-21 17:58:40 +01:00
'formats': formats,
2013-10-28 19:23:48 +01:00
'age_limit': 18,
2014-03-22 19:16:35 +01:00
}
2014-03-22 19:16:35 +01:00
class XTubeUserIE(InfoExtractor):
IE_DESC = 'XTube user profile'
_VALID_URL = r'https?://(?:www\.)?xtube\.com/community/profile\.php\?(.*?)user=(?P<username>[^&#]+)(?:$|[&#])'
_TEST = {
'url': 'http://www.xtube.com/community/profile.php?user=greenshowers',
'info_dict': {
'id': 'greenshowers',
'age_limit': 18,
},
'playlist_mincount': 155,
}
2014-03-22 19:16:35 +01:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
username = mobj.group('username')
profile_page = self._download_webpage(
url, username, note='Retrieving profile page')
video_count = int(self._search_regex(
2014-11-23 21:23:05 +01:00
r'<strong>%s\'s Videos \(([0-9]+)\)</strong>' % username, profile_page,
2014-03-22 19:16:35 +01:00
'video count'))
PAGE_SIZE = 25
urls = []
page_count = (video_count + PAGE_SIZE + 1) // PAGE_SIZE
for n in range(1, page_count + 1):
lpage_url = 'http://www.xtube.com/user_videos.php?page=%d&u=%s' % (n, username)
lpage = self._download_webpage(
lpage_url, username,
note='Downloading page %d/%d' % (n, page_count))
urls.extend(
re.findall(r'addthis:url="([^"]+)"', lpage))
return {
'_type': 'playlist',
'id': username,
'age_limit': 18,
2014-03-22 19:16:35 +01:00
'entries': [{
'_type': 'url',
'url': eurl,
'ie_key': 'XTube',
} for eurl in urls]
}