Miroirs/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-27 21:59:17 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

[cliphunter] Fix extraction and update test (Fixes #4362)

Browse source
This commit is contained in:
Naglis Jonaitis 2015-01-23 21:22:49 +02:00
parent 6896a52721
commit 3e055aa5c3
1 changed files with 23 additions and 33 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

56
youtube_dl/extractor/cliphunter.py
View file

@ -1,9 +1,7 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import determine_ext
_translation_table = {
@ -27,10 +25,10 @@ class CliphunterIE(InfoExtractor):
'''
_TEST = {
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
'md5': 'a2ba71eebf523859fe527a61018f723e',
'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
'info_dict': {
'id': '1012420',
'ext': 'mp4',
'ext': 'flv',
'title': 'Fun Jynx Maze solo',
'thumbnail': 're:^https?://.*\.jpg$',
'age_limit': 18,
@ -44,39 +42,31 @@ class CliphunterIE(InfoExtractor):
video_title = self._search_regex(
r'mediaTitle = "([^"]+)"', webpage, 'title')
pl_fiji = self._search_regex(
r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
pl_c_qual = self._search_regex(
r'pl_c_qual = "(.)"', webpage, 'video quality')
video_url = _decode(pl_fiji)
formats = [{
'url': video_url,
'format_id': 'default-%s' % pl_c_qual,
}]
fmts = {}
for fmt in ('mp4', 'flv'):
fmt_list = self._parse_json(self._search_regex(
r'var %sjson\s*=\s*(\[.*?\]);' % fmt, webpage, '%s formats' % fmt), video_id)
for f in fmt_list:
fmts[f['fname']] = _decode(f['sUrl'])
qualities_json = self._search_regex(
r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
qualities_data = json.loads(qualities_json)
qualities = self._parse_json(self._search_regex(
r'var player_btns\s*=\s*(.*?);\n', webpage, 'quality info'), video_id)
for i, t in enumerate(
re.findall(r"pl_fiji_([a-z0-9]+)\s*=\s*'([^']+')", webpage)):
quality_id, crypted_url = t
video_url = _decode(crypted_url)
formats = []
for fname, url in fmts.items():
f = {
'format_id': quality_id,
'url': video_url,
'quality': i,
'url': url,
}
if quality_id in qualities_data:
qd = qualities_data[quality_id]
m = re.match(
r'''(?x)<b>(?P<width>[0-9]+)x(?P<height>[0-9]+)<\\/b>
\s*\(\s*(?P<tbr>[0-9]+)\s*kb\\/s''', qd)
if m:
f['width'] = int(m.group('width'))
f['height'] = int(m.group('height'))
f['tbr'] = int(m.group('tbr'))
if fname in qualities:
qual = qualities[fname]
f.update({
'format_id': '%s_%sp' % (determine_ext(url), qual['h']),
'width': qual['w'],
'height': qual['h'],
'tbr': qual['br'],
})
formats.append(f)
self._sort_formats(formats)
thumbnail = self._search_regex(