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

[keezmovies] Fix extraction

Browse source 
Also fixes #7752
This commit is contained in:
Yen Chi Hsuan 2015-12-05 17:25:14 +08:00
parent ab3b773bbe
commit db9bd5267f
1 changed files with 24 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
youtube_dl/extractor/keezmovies.py
View file

@ -1,23 +1,25 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import os
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse from ..utils import (
from ..utils import sanitized_Request sanitized_Request,
url_basename,
)
class KeezMoviesIE(InfoExtractor): class KeezMoviesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)' _VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
_TEST = { _TEST = {
'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711', 'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
'md5': '6e297b7e789329923fcf83abb67c9289', 'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
'info_dict': { 'info_dict': {
'id': '1214711', 'id': '1214711',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Petite Asian Lady Mai Playing In Bathtub', 'title': 'Petite Asian Lady Mai Playing In Bathtub',
'age_limit': 18, 'age_limit': 18,
'thumbnail': 're:^https?://.*\.jpg$',
} }
} }
@ -36,21 +38,29 @@ class KeezMoviesIE(InfoExtractor):
video_title = self._html_search_regex( video_title = self._html_search_regex(
r'<h1 [^>]*>([^<]+)', webpage, 'title') r'<h1 [^>]*>([^<]+)', webpage, 'title')
video_url = self._html_search_regex( flashvars = self._parse_json(self._search_regex(
r'(?s)html5VideoPlayer = .*?src="([^"]+)"', webpage, 'video URL') r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id)
path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:] formats = []
format = path.split('/')[4].split('_')[:2] for height in (180, 240, 480):
format = "-".join(format) if flashvars.get('quality_%dp' % height):
video_url = flashvars['quality_%dp' % height]
a_format = {
'url': video_url,
'height': height,
'format_id': '%dp' % height,
}
filename_parts = url_basename(video_url).split('_')
if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]):
a_format['tbr'] = int(filename_parts[1][:-1])
formats.append(a_format)
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
return { return {
'id': video_id, 'id': video_id,
'title': video_title, 'title': video_title,
'url': video_url, 'formats': formats,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': age_limit, 'age_limit': age_limit,
'thumbnail': flashvars.get('image_url')
} }