summaryrefslogtreecommitdiffhomepage
diff options
context:
space:
mode:
authorSergey M․ <[email protected]>2014-04-04 22:45:39 +0700
committerSergey M․ <[email protected]>2014-04-04 22:45:39 +0700
commit4b9cced1034d6048bc859303db2e044e427dbeb1 (patch)
tree961103b0496ac51bfca2405b44c46819dc73e7ff
parent6344fa04bbee4dc2336c3ace134cd150fba2f7e6 (diff)
downloadyoutube-dl-4b9cced1034d6048bc859303db2e044e427dbeb1.tar.gz
youtube-dl-4b9cced1034d6048bc859303db2e044e427dbeb1.zip
[pornhd] Fix extraction (Closes #2693)
-rw-r--r--youtube_dl/extractor/pornhd.py75
1 files changed, 56 insertions, 19 deletions
diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index 58f9c690e..f0c175e9d 100644
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -1,44 +1,81 @@
from __future__ import unicode_literals
import re
+import json
from .common import InfoExtractor
-from ..utils import compat_urllib_parse
+from ..utils import int_or_none
class PornHdIE(InfoExtractor):
- _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<video_id>[0-9]+)/(?P<video_title>.+)'
+ _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)'
_TEST = {
'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
- 'file': '1962.flv',
'md5': '35272469887dca97abd30abecc6cdf75',
'info_dict': {
- "title": "sierra-day-gets-his-cum-all-over-herself-hd-porn-video",
- "age_limit": 18,
+ 'id': '1962',
+ 'ext': 'mp4',
+ 'title': 'Sierra loves doing laundry',
+ 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
+ 'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
-
- video_id = mobj.group('video_id')
- video_title = mobj.group('video_title')
+ video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
- next_url = self._html_search_regex(
- r'&hd=(http.+?)&', webpage, 'video URL')
- next_url = compat_urllib_parse.unquote(next_url)
+ title = self._og_search_title(webpage)
+ TITLE_SUFFIX = ' porn HD Video | PornHD.com '
+ if title.endswith(TITLE_SUFFIX):
+ title = title[:-len(TITLE_SUFFIX)]
+
+ description = self._html_search_regex(
+ r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
+ view_count = int_or_none(self._html_search_regex(
+ r'(\d+) views </span>', webpage, 'view count', fatal=False))
+
+ formats = [
+ {
+ 'url': url,
+ 'ext': format.lower(),
+ 'format_id': '%s-%s' % (format.lower(), quality.lower()),
+ 'quality': 1 if quality.lower() == 'high' else 0,
+ } for format, quality, url in re.findall(
+ r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
+ ]
+
+ mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
+ if mobj:
+ flashvars = json.loads(mobj.group('flashvars'))
+ formats.extend([
+ {
+ 'url': flashvars['hashlink'].replace('?noProxy=1', ''),
+ 'ext': 'flv',
+ 'format_id': 'flv-low',
+ 'quality': 0,
+ },
+ {
+ 'url': flashvars['hd'].replace('?noProxy=1', ''),
+ 'ext': 'flv',
+ 'format_id': 'flv-high',
+ 'quality': 1,
+ }
+ ])
+ thumbnail = flashvars['urlWallpaper']
+ else:
+ thumbnail = self._og_search_thumbnail(webpage)
- video_url = self._download_webpage(
- next_url, video_id, note='Retrieving video URL',
- errnote='Could not retrieve video URL')
- age_limit = 18
+ self._sort_formats(formats)
return {
'id': video_id,
- 'url': video_url,
- 'ext': 'flv',
- 'title': video_title,
- 'age_limit': age_limit,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'view_count': view_count,
+ 'formats': formats,
+ 'age_limit': 18,
}