Merge pull request #10829 from TRox1972/pornoxo_improve

[pornoxo] Use JWPlatform to improve metadata extraction
This commit is contained in:
Yen Chi Hsuan 2016-10-02 20:19:34 +08:00 committed by GitHub
commit 25291b979a
1 changed files with 12 additions and 19 deletions

View File

@ -2,13 +2,13 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .jwplatform import JWPlatformBaseIE
from ..utils import ( from ..utils import (
str_to_int, str_to_int,
) )
class PornoXOIE(InfoExtractor): class PornoXOIE(JWPlatformBaseIE):
_VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html' _VALID_URL = r'https?://(?:www\.)?pornoxo\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)\.html'
_TEST = { _TEST = {
'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html', 'url': 'http://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary.html',
@ -17,7 +17,8 @@ class PornoXOIE(InfoExtractor):
'id': '7564', 'id': '7564',
'ext': 'flv', 'ext': 'flv',
'title': 'Striptease From Sexy Secretary!', 'title': 'Striptease From Sexy Secretary!',
'description': 'Striptease From Sexy Secretary!', 'display_id': 'striptease-from-sexy-secretary',
'description': 'md5:0ee35252b685b3883f4a1d38332f9980',
'categories': list, # NSFW 'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$', 'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18, 'age_limit': 18,
@ -26,23 +27,14 @@ class PornoXOIE(InfoExtractor):
def _real_extract(self, url): 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, display_id = mobj.groups()
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_data = self._extract_jwplayer_data(webpage, video_id, require_title=False)
video_url = self._html_search_regex(
r'\'file\'\s*:\s*"([^"]+)"', webpage, 'video_url')
title = self._html_search_regex( title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title') r'<title>([^<]+)\s*-\s*PornoXO', webpage, 'title')
description = self._html_search_regex(
r'<meta name="description" content="([^"]+)\s*featuring',
webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'\'image\'\s*:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
view_count = str_to_int(self._html_search_regex( view_count = str_to_int(self._html_search_regex(
r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False)) r'[vV]iews:\s*([0-9,]+)', webpage, 'view count', fatal=False))
@ -53,13 +45,14 @@ class PornoXOIE(InfoExtractor):
None if categories_str is None None if categories_str is None
else categories_str.split(',')) else categories_str.split(','))
return { video_data.update({
'id': video_id, 'id': video_id,
'url': video_url,
'title': title, 'title': title,
'description': description, 'display_id': display_id,
'thumbnail': thumbnail, 'description': self._html_search_meta('description', webpage),
'categories': categories, 'categories': categories,
'view_count': view_count, 'view_count': view_count,
'age_limit': 18, 'age_limit': 18,
} })
return video_data