1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-27 19:36:50 +01:00

Move XVideos IE into its own file (and simplify it a bit)

This commit is contained in:
Philipp Hagemeister 2013-06-23 21:11:47 +02:00
parent 7beb36a529
commit cbf46c737c
2 changed files with 44 additions and 43 deletions

View File

@ -37,54 +37,12 @@ from .extractor.statigram import StatigramIE
from .extractor.photobucket import PhotobucketIE
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
from .extractor.vimeo import VimeoIE
from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
from .extractor.youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
from .extractor.zdf import ZDFIE
class XVideosIE(InfoExtractor):
"""Information extractor for xvideos.com"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
IE_NAME = u'xvideos'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
# Extract video URL
video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
webpage, u'video URL'))
# Extract title
video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
webpage, u'title')
# Extract video thumbnail
video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
webpage, u'thumbnail', fatal=False)
info = {
'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': None,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
'description': None,
}
return [info]
class InfoQIE(InfoExtractor):
"""Information extractor for infoq.com"""

View File

@ -0,0 +1,43 @@
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
)
class XVideosIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
# Extract video URL
video_url = compat_urllib_parse.unquote(self._search_regex(r'flv_url=(.+?)&',
webpage, u'video URL'))
# Extract title
video_title = self._html_search_regex(r'<title>(.*?)\s+-\s+XVID',
webpage, u'title')
# Extract video thumbnail
video_thumbnail = self._search_regex(r'http://(?:img.*?\.)xvideos.com/videos/thumbs/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/[a-fA-F0-9]+/([a-fA-F0-9.]+jpg)',
webpage, u'thumbnail', fatal=False)
info = {
'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': None,
'title': video_title,
'ext': 'flv',
'thumbnail': video_thumbnail,
'description': None,
}
return [info]