youtube-dl/youtube_dl/extractor/cracked.py

81 lines
2.7 KiB
Python
Raw Normal View History

2014-07-16 06:45:42 -07:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
str_to_int,
)
2014-07-16 06:45:42 -07:00
class CrackedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
2014-07-16 06:45:42 -07:00
_TEST = {
'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
'md5': '4b29a5eeec292cd5eca6388c7558db9e',
2014-07-16 06:45:42 -07:00
'info_dict': {
'id': '19006',
2014-07-16 06:45:42 -07:00
'ext': 'mp4',
'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies',
'description': 'md5:3b909e752661db86007d10e5ec2df769',
'timestamp': 1405659600,
'upload_date': '20140718',
2014-07-16 06:45:42 -07:00
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
youtube_url = self._search_regex(
r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
webpage, 'youtube url', default=None)
if youtube_url:
return self.url_result(youtube_url)
video_url = self._html_search_regex(
[r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],
webpage, 'video URL')
2014-07-16 06:45:42 -07:00
2015-04-23 08:44:51 -07:00
title = self._search_regex(
[r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
webpage, 'title')
2014-07-16 06:45:42 -07:00
2015-04-23 08:44:51 -07:00
description = self._search_regex(
r'name="?(?:og:)?description"?\s+content="([^"]+)"',
webpage, 'description', default=None)
timestamp = self._html_search_regex(
r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
if timestamp:
timestamp = parse_iso8601(timestamp[:-6])
2014-07-16 06:45:42 -07:00
view_count = str_to_int(self._html_search_regex(
2015-04-23 08:44:51 -07:00
r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
2015-04-23 08:44:51 -07:00
r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
webpage, 'comment count', fatal=False))
2014-07-16 06:45:42 -07:00
m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
if m:
width = int(m.group('width'))
height = int(m.group('height'))
else:
width = height = None
2014-07-16 06:45:42 -07:00
return {
'id': video_id,
2014-11-23 11:41:03 -08:00
'url': video_url,
'title': title,
'description': description,
'timestamp': timestamp,
'view_count': view_count,
'comment_count': comment_count,
'height': height,
'width': width,
2014-11-23 11:41:03 -08:00
}