[hellporno] Extract all formats and improve

This commit is contained in:
Sergey M․ 2014-12-29 21:33:41 +06:00
parent 03d9aad87c
commit 355e41466d
1 changed files with 33 additions and 14 deletions

View File

@ -1,5 +1,12 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
js_to_json,
remove_end,
)
class HellPornoIE(InfoExtractor): class HellPornoIE(InfoExtractor):
@ -19,23 +26,36 @@ class HellPornoIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex( title = remove_end(self._html_search_regex(
r'video_id:\s*\'([^\']+)\'', webpage, 'id') r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
ext = self._html_search_regex( flashvars = self._parse_json(self._search_regex(
r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:] r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
display_id, transform_source=js_to_json)
video_url = self._html_search_regex( video_id = flashvars.get('video_id')
r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') thumbnail = flashvars.get('preview_url')
ext = flashvars.get('postfix', '.mp4')[1:]
title = self._html_search_regex( formats = []
r'<title>([^<]+)\s*-\s*Hell Porno</title>', webpage, 'title') for video_url_key in ['video_url', 'video_alt_url']:
video_url = flashvars.get(video_url_key)
thumbnail = self._html_search_regex( if not video_url:
r'preview_url:\s*\'([^\']+)\'', continue
webpage, 'thumbnail', fatal=False) video_text = flashvars.get('%s_text' % video_url_key)
fmt = {
'url': video_url,
'ext': ext,
'format_id': video_text,
}
m = re.search(r'^(?P<height>\d+)[pP]', video_text)
if m:
fmt['height'] = int(m.group('height'))
formats.append(fmt)
self._sort_formats(formats)
categories = self._html_search_meta( categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',') 'keywords', webpage, 'categories', default='').split(',')
@ -43,10 +63,9 @@ class HellPornoIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'url': video_url,
'title': title, 'title': title,
'ext': ext,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'categories': categories, 'categories': categories,
'age_limit': 18, 'age_limit': 18,
'formats': formats,
} }