w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[anysex] Simplify and extract more metadata

Browse source
This commit is contained in:
Sergey M․ 2014-08-31 07:05:53 +07:00
parent be2dd0651e
commit 35241d05d1
1 changed files with 28 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

39
youtube_dl/extractor/anysex.py
View file

@ -1,13 +1,16 @@
# coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import (
parse_duration,
int_or_none,
)
class AnySexIE(InfoExtractor): class AnySexIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?anysex\.com/(?P<id>\d+)/?' _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://anysex.com/156592/', 'url': 'http://anysex.com/156592/',
'md5': '023e9fbb7f7987f5529a394c34ad3d3d', 'md5': '023e9fbb7f7987f5529a394c34ad3d3d',
@ -15,6 +18,8 @@ class AnySexIE(InfoExtractor):
'id': '156592', 'id': '156592',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Busty and sexy blondie in her bikini strips for you', 'title': 'Busty and sexy blondie in her bikini strips for you',
'description': 'md5:de9e418178e2931c10b62966474e1383',
'categories': ['Erotic'],
'duration': 270, 'duration': 270,
} }
} }
@ -24,20 +29,32 @@ class AnySexIE(InfoExtractor):
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
video_url = self._html_search_regex(r'video_url: \'(.*?)\',', webpage, 'video_url') description = self._html_search_regex(
thumbnail = self._html_search_regex(r'preview_url: \'(.*?)\',', webpage, 'thumbnail') r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
mobj = re.search(r'<b>Duration:</b> (?P<minutes>\d+):(?P<seconds>\d+)<', webpage) categories = re.findall(
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
view_count = self._html_search_regex(r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False) duration = parse_duration(self._search_regex(
r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex(
r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
return { return {
'id': video_id, 'id': video_id,
'ext': 'mp4',
'url': video_url, 'url': video_url,
'ext': 'mp4',
'title': title, 'title': title,
'duration': int_or_none(duration), 'description': description,
'view_count': int_or_none(view_count), 'thumbnail': thumbnail,
'categories': categories,
'duration': duration,
'view_count': view_count,
} }