github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[hellporno] simplify

Browse source
This commit is contained in:
peugeot 2014-12-29 10:38:07 +01:00
parent 6a1c4fbfcb
commit 513fd2a872
1 changed files with 14 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
youtube_dl/extractor/hellporno.py
View file

@ -1,55 +1,51 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class HellPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<display_id>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<id>[^/]+)'
_TEST = {
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
'md5': '1fee339c610d2049699ef2aa699439f1',
'info_dict': {
'id': '149116',
'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
'ext': 'mp4',
'title': 'Dixie is posing with naked ass very erotic',
'description': 'md5:5ba02cbf31eff820147b3cc25306d89a',
'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$',
'age_limit': 18,
}
}
def _real_extract(self, url):
webpage = self._download_webpage(url, 'main')
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(r'video_id:\s*\'([^\']+)\'', webpage, 'id')
video_id = self._html_search_regex(
r'video_id:\s*\'([^\']+)\'', webpage, 'id')
video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url')
ext = self._html_search_regex(
r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:]
ext = self._html_search_regex(r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:]
video_url = self._html_search_regex(
r'video_url:\s*\'([^\']+)\'', webpage, 'video_url')
title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*Hell Porno</title>', webpage, 'title')
description = self._html_search_meta('description', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'preview_url:\s*\'([^\']+)\'',
webpage, 'thumbnail', fatal=False)
categories_str = self._html_search_regex(
r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
categories = (
None if categories_str is None
else categories_str.split(','))
categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'ext': ext,
'description': description,
'thumbnail': thumbnail,
'categories': categories,
'age_limit': 18,