[watchindianporn] Fix extraction (closes #13411)

This commit is contained in:
Giuseppe Fabiano 2017-06-19 23:30:45 +02:00 committed by Sergey M
parent 6ce79d7ac0
commit 048b55804d

View File

@ -4,11 +4,7 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import parse_duration
unified_strdate,
parse_duration,
int_or_none,
)
class WatchIndianPornIE(InfoExtractor): class WatchIndianPornIE(InfoExtractor):
@ -23,11 +19,8 @@ class WatchIndianPornIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Hot milf from kerala shows off her gorgeous large breasts on camera', 'title': 'Hot milf from kerala shows off her gorgeous large breasts on camera',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'LoveJay',
'upload_date': '20160428',
'duration': 226, 'duration': 226,
'view_count': int, 'view_count': int,
'comment_count': int,
'categories': list, 'categories': list,
'age_limit': 18, 'age_limit': 18,
} }
@ -40,51 +33,36 @@ class WatchIndianPornIE(InfoExtractor):
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
video_url = self._html_search_regex( info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
r"url: escape\('([^']+)'\)", webpage, 'url')
title = self._html_search_regex( title = self._html_search_regex((
r'<h2 class="he2"><span>(.*?)</span>', r'<title>(.+?)\s*-\s*Indian\s+Porn</title>',
webpage, 'title') r'<h4>(.+?)</h4>'
thumbnail = self._html_search_regex( ), webpage, 'title')
r'<span id="container"><img\s+src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
uploader = self._html_search_regex(
r'class="aupa">\s*(.*?)</a>',
webpage, 'uploader')
upload_date = unified_strdate(self._html_search_regex(
r'Added: <strong>(.+?)</strong>', webpage, 'upload date', fatal=False))
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'<td>Time:\s*</td>\s*<td align="right"><span>\s*(.+?)\s*</span>', r'Time:\s*<strong>\s*(.+?)\s*</strong>',
webpage, 'duration', fatal=False)) webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex( view_count = int(self._search_regex(
r'<td>Views:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>', r'(?s)Time:\s*<strong>.*?</strong>.*?<strong>\s*(\d+)\s*</strong>',
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
comment_count = int_or_none(self._search_regex(
r'<td>Comments:\s*</td>\s*<td align="right"><span>\s*(\d+)\s*</span>',
webpage, 'comment count', fatal=False))
categories = re.findall( categories = re.findall(
r'<a href="[^"]+/search/video/desi"><span>([^<]+)</span></a>', r'<a[^>]+class=[\'"]categories[\'"][^>]*>\s*([^<]+)\s*</a>',
webpage) webpage)
return { info_dict.update({
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'url': video_url,
'http_headers': { 'http_headers': {
'Referer': url, 'Referer': url,
}, },
'title': title, 'title': title,
'thumbnail': thumbnail,
'uploader': uploader,
'upload_date': upload_date,
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,
'comment_count': comment_count,
'categories': categories, 'categories': categories,
'age_limit': 18, 'age_limit': 18,
} })
return info_dict