ansol/youtube-dl
7
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 21:35:47 +00:00
Code Issues Projects Releases Wiki Activity

[xtube] Fix and modernize (Closes #4489)

Browse Source
This commit is contained in:
Sergey M․ 2014-12-19 21:56:44 +06:00
parent a2a4bae929
commit 16ea817968
1 changed files with 35 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
youtube_dl/extractor/xtube.py
View File

@ -1,11 +1,11 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_request, compat_urllib_request,
compat_urllib_parse,
) )
from ..utils import ( from ..utils import (
parse_duration, parse_duration,
@ -14,7 +14,7 @@ from ..utils import (
class XTubeIE(InfoExtractor): class XTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&]+))' _VALID_URL = r'https?://(?:www\.)?(?P<url>xtube\.com/watch\.php\?v=(?P<id>[^/?&#]+))'
_TEST = { _TEST = {
'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_', 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_',
'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab', 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab',
@ -30,41 +30,49 @@ class XTubeIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url) req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1') req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id) webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<p class="title">([^<]+)', webpage, 'title') video_title = self._html_search_regex(
r'<p class="title">([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex( video_uploader = self._html_search_regex(
r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False) [r"var\s+contentOwnerId\s*=\s*'([^']+)",
r'By:\s*<a href="/community/profile\.php?user=([^"]+)'],
webpage, 'uploader', fatal=False)
video_description = self._html_search_regex( video_description = self._html_search_regex(
r'<p class="fieldsDesc">([^<]+)', webpage, 'description', fatal=False) r'<p class="fieldsDesc">([^<]+)',
webpage, 'description', fatal=False)
duration = parse_duration(self._html_search_regex( duration = parse_duration(self._html_search_regex(
r'<span class="bold">Runtime:</span> ([^<]+)</p>', webpage, 'duration', fatal=False)) r'<span class="bold">Runtime:</span> ([^<]+)</p>',
view_count = self._html_search_regex( webpage, 'duration', fatal=False))
r'<span class="bold">Views:</span> ([\d,\.]+)</p>', webpage, 'view count', fatal=False) view_count = str_to_int(self._html_search_regex(
if view_count: r'<span class="bold">Views:</span> ([\d,\.]+)</p>',
view_count = str_to_int(view_count) webpage, 'view count', fatal=False))
comment_count = self._html_search_regex( comment_count = str_to_int(self._html_search_regex(
r'<div id="commentBar">([\d,\.]+) Comments</div>', webpage, 'comment count', fatal=False) r'<div id="commentBar">([\d,\.]+) Comments</div>',
if comment_count: webpage, 'comment count', fatal=False))
comment_count = str_to_int(comment_count)
player_quality_option = json.loads(self._html_search_regex( formats = []
r'playerQualityOption = ({.+?});', webpage, 'player quality option')) for format_id, video_url in re.findall(
r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage):
QUALITIES = ['3gp', 'mp4_normal', 'mp4_high', 'flv', 'mp4_ultra', 'mp4_720', 'mp4_1080'] fmt = {
formats = [ 'url': compat_urllib_parse.unquote(video_url),
{
'url': furl,
'format_id': format_id, 'format_id': format_id,
'preference': QUALITIES.index(format_id) if format_id in QUALITIES else -1, }
} for format_id, furl in player_quality_option.items() 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})
self._sort_formats(formats) self._sort_formats(formats)
return { return {