mirror of https://github.com/blackjack4494/yt-dlc
[goshgay] Fix extraction
This commit is contained in:
parent
73aeb2dc56
commit
82b34105d3
|
@ -2,22 +2,25 @@
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..compat import compat_urlparse
|
from ..compat import (
|
||||||
|
compat_parse_qs,
|
||||||
|
)
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
ExtractorError,
|
parse_duration,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class GoshgayIE(InfoExtractor):
|
class GoshgayIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)'
|
_VALID_URL = r'https?://www\.goshgay\.com/video(?P<id>\d+?)($|/)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'http://www.goshgay.com/video4116282',
|
'url': 'http://www.goshgay.com/video299069/diesel_sfw_xxx_video',
|
||||||
'md5': '268b9f3c3229105c57859e166dd72b03',
|
'md5': '027fcc54459dff0feb0bc06a7aeda680',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '4116282',
|
'id': '299069',
|
||||||
'ext': 'flv',
|
'ext': 'flv',
|
||||||
'title': 'md5:089833a4790b5e103285a07337f245bf',
|
'title': 'DIESEL SFW XXX Video',
|
||||||
'thumbnail': 're:http://.*\.jpg',
|
'thumbnail': 're:^http://.*\.jpg$',
|
||||||
|
'duration': 79,
|
||||||
'age_limit': 18,
|
'age_limit': 18,
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
@ -26,33 +29,25 @@ class GoshgayIE(InfoExtractor):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, video_id)
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
title = self._og_search_title(webpage)
|
title = self._html_search_regex(
|
||||||
thumbnail = self._og_search_thumbnail(webpage)
|
r'<h2>(.*?)<', webpage, 'title')
|
||||||
|
duration = parse_duration(self._html_search_regex(
|
||||||
|
r'<span class="duration">\s*-?\s*(.*?)</span>',
|
||||||
|
webpage, 'duration', fatal=False))
|
||||||
family_friendly = self._html_search_meta(
|
family_friendly = self._html_search_meta(
|
||||||
'isFamilyFriendly', webpage, default='false')
|
'isFamilyFriendly', webpage, default='false')
|
||||||
config_url = self._search_regex(
|
|
||||||
r"'config'\s*:\s*'([^']+)'", webpage, 'config URL')
|
|
||||||
|
|
||||||
config = self._download_xml(
|
flashvars = compat_parse_qs(self._html_search_regex(
|
||||||
config_url, video_id, 'Downloading player config XML')
|
r'<embed.+?id="flash-player-embed".+?flashvars="([^"]+)"',
|
||||||
|
webpage, 'flashvars'))
|
||||||
if config is None:
|
thumbnail = flashvars.get('url_bigthumb', [None])[0]
|
||||||
raise ExtractorError('Missing config XML')
|
video_url = flashvars['flv_url'][0]
|
||||||
if config.tag != 'config':
|
|
||||||
raise ExtractorError('Missing config attribute')
|
|
||||||
fns = config.findall('file')
|
|
||||||
if len(fns) < 1:
|
|
||||||
raise ExtractorError('Missing media URI')
|
|
||||||
video_url = fns[0].text
|
|
||||||
|
|
||||||
url_comp = compat_urlparse.urlparse(url)
|
|
||||||
ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2])
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'url': video_url,
|
'url': video_url,
|
||||||
'title': title,
|
'title': title,
|
||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
'http_referer': ref,
|
'duration': duration,
|
||||||
'age_limit': 0 if family_friendly == 'true' else 18,
|
'age_limit': 0 if family_friendly == 'true' else 18,
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue