[spankwire] Use centralized format sorting and unicode_literals

This commit is contained in:
Philipp Hagemeister 2014-01-17 03:25:59 +01:00
parent befdc8f3b6
commit 9ac0a67581
1 changed files with 24 additions and 14 deletions

View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import os
import re
@ -11,17 +13,18 @@ from ..aes import (
aes_decrypt_text
)
class SpankwireIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
_TEST = {
u'url': u'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
u'file': u'103545.mp4',
u'md5': u'1b3f55e345500552dbc252a3e9c1af43',
u'info_dict': {
u"uploader": u"oreusz",
u"title": u"Buckcherry`s X Rated Music Video Crazy Bitch",
u"description": u"Crazy Bitch X rated music video.",
u"age_limit": 18,
'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
'file': '103545.mp4',
'md5': '1b3f55e345500552dbc252a3e9c1af43',
'info_dict': {
"uploader": "oreusz",
"title": "Buckcherry`s X Rated Music Video Crazy Bitch",
"description": "Crazy Bitch X rated music video.",
"age_limit": 18,
}
}
@ -34,17 +37,17 @@ class SpankwireIE(InfoExtractor):
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, u'title')
video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
video_uploader = self._html_search_regex(
r'by:\s*<a [^>]*>(.+?)</a>', webpage, u'uploader', fatal=False)
r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
thumbnail = self._html_search_regex(
r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False)
r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
description = self._html_search_regex(
r'<div\s+id="descriptionContent">([^<]+)<', webpage, u'description', fatal=False)
r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False)
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
if webpage.find('flashvars\.encrypted = "true"') != -1:
password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, u'password').replace('+', ' ')
password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ')
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
formats = []
@ -52,14 +55,21 @@ class SpankwireIE(InfoExtractor):
path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:]
format = path.split('/')[4].split('_')[:2]
resolution, bitrate_str = format
format = "-".join(format)
height = int(resolution.rstrip('P'))
tbr = int(bitrate_str.rstrip('K'))
formats.append({
'url': video_url,
'ext': extension,
'resolution': resolution,
'format': format,
'tbr': tbr,
'height': height,
'format_id': format,
})
formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
self._sort_formats(formats)
age_limit = self._rta_search(webpage)