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

[pornhub] Use compat_urllib_parse_unquote and compat_urllib_parse_unquote_plus

Browse source
This commit is contained in:
Sergey M․ 2015-07-17 23:47:23 +06:00
parent 388ad0c05c
commit 605cbef653
1 changed files with 5 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
youtube_dl/extractor/pornhub.py
View file

@ -5,7 +5,8 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse, compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
compat_urllib_request, compat_urllib_request,
) )
@ -69,7 +70,7 @@ class PornHubIE(InfoExtractor):
webpage, 'uploader', fatal=False) webpage, 'uploader', fatal=False)
thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, '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)
view_count = self._extract_count( view_count = self._extract_count(
r'<span class="count">([\d,\.]+)</span> views', webpage, 'view') r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
@ -80,9 +81,9 @@ class PornHubIE(InfoExtractor):
comment_count = self._extract_count( comment_count = self._extract_count(
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment') r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
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 = compat_urllib_parse.unquote_plus( password = compat_urllib_parse_unquote_plus(
self._search_regex(r'"video_title":"([^"]+)', webpage, 'password')) self._search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
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))