summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorPhilipp Hagemeister <[email protected]>2013-06-23 22:32:44 +0200
committerPhilipp Hagemeister <[email protected]>2013-06-23 22:32:44 +0200
commitcb10cded2a00b9a51eed88ae10bb78d93edd0894 (patch)
treeb432d38a52d19a0a2cfcd0286a6a0c0e4a067284
parentcd8b83029287fa9ad1385be4ecb32d52b5f545aa (diff)
downloadyoutube-dl-cb10cded2a00b9a51eed88ae10bb78d93edd0894.tar.gz
youtube-dl-cb10cded2a00b9a51eed88ae10bb78d93edd0894.zip
[xhamster] Move into own file
-rwxr-xr-xyoutube_dl/InfoExtractors.py52
-rw-r--r--youtube_dl/extractor/xhamster.py61
2 files changed, 62 insertions, 51 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 300bd7a72..66a5b0093 100755
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -66,6 +66,7 @@ from .extractor.vimeo import VimeoIE
from .extractor.vine import VineIE
from .extractor.worldstarhiphop import WorldStarHipHopIE
from .extractor.xnxx import XNXXIE
+from .extractor.xhamster import XHamsterIE
from .extractor.xvideos import XVideosIE
from .extractor.yahoo import YahooIE, YahooSearchIE
from .extractor.youjizz import YouJizzIE
@@ -113,57 +114,6 @@ from .extractor.zdf import ZDFIE
-class XHamsterIE(InfoExtractor):
- """Information Extractor for xHamster"""
- _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
-
- def _real_extract(self,url):
- mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group('id')
- mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
- webpage = self._download_webpage(mrss_url, video_id)
-
- mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
- if mobj is None:
- raise ExtractorError(u'Unable to extract media URL')
- if len(mobj.group('server')) == 0:
- video_url = compat_urllib_parse.unquote(mobj.group('file'))
- else:
- video_url = mobj.group('server')+'/key='+mobj.group('file')
- video_extension = video_url.split('.')[-1]
-
- video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
- webpage, u'title')
-
- # Can't see the description anywhere in the UI
- # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
- # webpage, u'description', fatal=False)
- # if video_description: video_description = unescapeHTML(video_description)
-
- mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
- if mobj:
- video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
- else:
- video_upload_date = None
- self._downloader.report_warning(u'Unable to extract upload date')
-
- video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
- webpage, u'uploader id', default=u'anonymous')
-
- video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
- webpage, u'thumbnail', fatal=False)
-
- return [{
- 'id': video_id,
- 'url': video_url,
- 'ext': video_extension,
- 'title': video_title,
- # 'description': video_description,
- 'upload_date': video_upload_date,
- 'uploader_id': video_uploader_id,
- 'thumbnail': video_thumbnail
- }]
diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py
new file mode 100644
index 000000000..001350926
--- /dev/null
+++ b/youtube_dl/extractor/xhamster.py
@@ -0,0 +1,61 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urllib_parse,
+
+ ExtractorError,
+)
+
+
+class XHamsterIE(InfoExtractor):
+ """Information Extractor for xHamster"""
+ _VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
+
+ def _real_extract(self,url):
+ mobj = re.match(self._VALID_URL, url)
+
+ video_id = mobj.group('id')
+ mrss_url = 'http://xhamster.com/movies/%s/.html' % video_id
+ webpage = self._download_webpage(mrss_url, video_id)
+
+ mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
+ if mobj is None:
+ raise ExtractorError(u'Unable to extract media URL')
+ if len(mobj.group('server')) == 0:
+ video_url = compat_urllib_parse.unquote(mobj.group('file'))
+ else:
+ video_url = mobj.group('server')+'/key='+mobj.group('file')
+ video_extension = video_url.split('.')[-1]
+
+ video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
+ webpage, u'title')
+
+ # Can't see the description anywhere in the UI
+ # video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
+ # webpage, u'description', fatal=False)
+ # if video_description: video_description = unescapeHTML(video_description)
+
+ mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
+ if mobj:
+ video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
+ else:
+ video_upload_date = None
+ self._downloader.report_warning(u'Unable to extract upload date')
+
+ video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
+ webpage, u'uploader id', default=u'anonymous')
+
+ video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'',
+ webpage, u'thumbnail', fatal=False)
+
+ return [{
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': video_extension,
+ 'title': video_title,
+ # 'description': video_description,
+ 'upload_date': video_upload_date,
+ 'uploader_id': video_uploader_id,
+ 'thumbnail': video_thumbnail
+ }]