w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[pornhub] Use centralized sorting

Browse source
This commit is contained in:
Philipp Hagemeister 2014-01-07 10:25:34 +01:00
parent 84c92dc00f
commit 9933b57430
2 changed files with 27 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
youtube_dl/extractor/common.py
View file

@ -501,6 +501,7 @@ class InfoExtractor(object):
f.get('height') if f.get('height') is not None else -1, f.get('height') if f.get('height') is not None else -1,
f.get('width') if f.get('width') is not None else -1, f.get('width') if f.get('width') is not None else -1,
ext_preference, ext_preference,
f.get('tbr') if f.get('tbr') is not None else -1,
f.get('vbr') if f.get('vbr') is not None else -1, f.get('vbr') if f.get('vbr') is not None else -1,
f.get('abr') if f.get('abr') is not None else -1, f.get('abr') if f.get('abr') is not None else -1,
audio_ext_preference, audio_ext_preference,

38
youtube_dl/extractor/pornhub.py
View file

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import os import os
import re import re
@ -11,16 +13,17 @@ from ..aes import (
aes_decrypt_text aes_decrypt_text
) )
class PornHubIE(InfoExtractor): class PornHubIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))' _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))'
_TEST = { _TEST = {
u'url': u'http://www.pornhub.com/view_video.php?viewkey=648719015', 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
u'file': u'648719015.mp4', 'file': '648719015.mp4',
u'md5': u'882f488fa1f0026f023f33576004a2ed', 'md5': '882f488fa1f0026f023f33576004a2ed',
u'info_dict': { 'info_dict': {
u"uploader": u"BABES-COM", "uploader": "BABES-COM",
u"title": u"Seductive Indian beauty strips down and fingers her pink pussy", "title": "Seductive Indian beauty strips down and fingers her pink pussy",
u"age_limit": 18 "age_limit": 18
} }
} }
@ -33,15 +36,15 @@ class PornHubIE(InfoExtractor):
req.add_header('Cookie', 'age_verified=1') req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id) 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'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, u'uploader', fatal=False) video_uploader = self._html_search_regex(r'<b>From: </b>(?:\s|<[^>]*>)*(.+?)<', webpage, 'uploader', fatal=False)
thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, u'thumbnail', fatal=False) thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
if thumbnail: if thumbnail:
thumbnail = compat_urllib_parse.unquote(thumbnail) thumbnail = compat_urllib_parse.unquote(thumbnail)
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
if webpage.find('"encrypted":true') != -1: if webpage.find('"encrypted":true') != -1:
password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, u'password').replace('+', ' ') password = self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password').replace('+', ' ')
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
formats = [] formats = []
@ -50,13 +53,24 @@ class PornHubIE(InfoExtractor):
extension = os.path.splitext(path)[1][1:] extension = os.path.splitext(path)[1][1:]
format = path.split('/')[5].split('_')[:2] format = path.split('/')[5].split('_')[:2]
format = "-".join(format) format = "-".join(format)
m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
if m is None:
height = None
tbr = None
else:
height = int(m.group('height'))
tbr = int(m.group('tbr'))
formats.append({ formats.append({
'url': video_url, 'url': video_url,
'ext': extension, 'ext': extension,
'format': format, 'format': format,
'format_id': format, 'format_id': format,
'tbr': tbr,
'height': height,
}) })
formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-')))) self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,