R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[anysex] Improve metadata extraction

Browse Source
This commit is contained in:
Déstin Reed 2016-10-01 14:44:33 +02:00
parent ce032ddae4
commit d955ee4a71
1 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
youtube_dl/extractor/anysex.py
View File

@ -4,8 +4,11 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
parse_duration, get_element_by_attribute,
get_element_by_class,
int_or_none, int_or_none,
parse_duration,
js_to_json,
) )
@ -19,6 +22,7 @@ class AnySexIE(InfoExtractor):
'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', 'description': 'md5:de9e418178e2931c10b62966474e1383',
'thumbnail': 're:^https?://.*\.jpg$',
'categories': ['Erotic'], 'categories': ['Erotic'],
'duration': 270, 'duration': 270,
'age_limit': 18, 'age_limit': 18,
@ -26,24 +30,20 @@ class AnySexIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
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') video_data = self._parse_json(self._search_regex(
r'var\s+flashvars\s*=\s*({[^}]+});', webpage, 'video data'),
video_id, transform_source=js_to_json)
video_url = video_data['video_url']
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
description = self._html_search_regex(
r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
categories = re.findall( categories = re.findall(
r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage) r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex( duration = parse_duration(get_element_by_attribute('itemprop', 'duration', webpage))
r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False)) r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))
@ -52,8 +52,8 @@ class AnySexIE(InfoExtractor):
'url': video_url, 'url': video_url,
'ext': 'mp4', 'ext': 'mp4',
'title': title, 'title': title,
'description': description, 'description': get_element_by_class('description', webpage),
'thumbnail': thumbnail, 'thumbnail': video_data.get('preview_url'),
'categories': categories, 'categories': categories,
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,