github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 16:10:24 -05:00
Code Issues Projects Releases Packages Wiki Activity

[hornbunny] Simplify and add age_limit

Browse source
This commit is contained in:
Philipp Hagemeister 2014-09-01 23:04:36 +02:00
parent 11342b54d6
commit e4039057be
1 changed files with 23 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

34
youtube_dl/extractor/hornbunny.py
View file

@ -4,7 +4,11 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import (
int_or_none,
parse_duration,
)
class HornBunnyIE(InfoExtractor): class HornBunnyIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html' _VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
@ -15,7 +19,8 @@ class HornBunnyIE(InfoExtractor):
'id': '5227', 'id': '5227',
'ext': 'flv', 'ext': 'flv',
'title': 'panty slut jerk off instruction', 'title': 'panty slut jerk off instruction',
'duration': 550 'duration': 550,
'age_limit': 18,
} }
} }
@ -23,16 +28,22 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(
title = self._html_search_regex(r'class="title">(.*?)</h2>', webpage, 'title') url, video_id, note='Downloading initial webpage')
redirect_url = self._html_search_regex(r'pg&settings=(.*?)\|0"\);', webpage, 'title') title = self._html_search_regex(
r'class="title">(.*?)</h2>', webpage, 'title')
redirect_url = self._html_search_regex(
r'pg&settings=(.*?)\|0"\);', webpage, 'title')
webpage2 = self._download_webpage(redirect_url, video_id) webpage2 = self._download_webpage(redirect_url, video_id)
video_url = self._html_search_regex(r'flvMask:(.*?);', webpage2, 'video_url') video_url = self._html_search_regex(
r'flvMask:(.*?);', webpage2, 'video_url')
mobj = re.search(r'<strong>Runtime:</strong> (?P<minutes>\d+):(?P<seconds>\d+)</div>', webpage) duration = parse_duration(self._search_regex(
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
webpage, 'duration', fatal=False))
view_count = self._html_search_regex(r'<strong>Views:</strong> (\d+)</div>', webpage, 'view count', fatal=False) view_count = int_or_none(self._search_regex(
r'<strong>Views:</strong>\s*(\d+)</div>',
webpage, 'view count', fatal=False))
return { return {
'id': video_id, 'id': video_id,
@ -40,5 +51,6 @@ def _real_extract(self, url):
'title': title, 'title': title,
'ext': 'flv', 'ext': 'flv',
'duration': duration, 'duration': duration,
'view_count': int_or_none(view_count), 'view_count': view_count,
'age_limit': 18,
} }