yt-dlp/youtube_dl/extractor/cliphunter.py

93 lines
2.8 KiB
Python
Raw Normal View History

2014-01-27 06:55:30 +00:00
from __future__ import unicode_literals
import json
2014-01-25 00:46:52 +00:00
import re
from .common import InfoExtractor
2014-02-02 11:03:36 +00:00
2014-01-25 00:46:52 +00:00
_translation_table = {
2014-01-27 11:39:39 +00:00
'a': 'h', 'd': 'e', 'e': 'v', 'f': 'o', 'g': 'f', 'i': 'd', 'l': 'n',
'm': 'a', 'n': 'm', 'p': 'u', 'q': 't', 'r': 's', 'v': 'p', 'x': 'r',
'y': 'l', 'z': 'i',
'$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
}
2014-01-25 00:46:52 +00:00
def _decode(s):
return ''.join(_translation_table.get(c, c) for c in s)
2014-01-25 00:46:52 +00:00
class CliphunterIE(InfoExtractor):
2014-01-27 06:55:30 +00:00
IE_NAME = 'cliphunter'
2014-01-25 00:46:52 +00:00
2014-01-27 11:39:39 +00:00
_VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
(?P<id>[0-9]+)/
(?P<seo>.+?)(?:$|[#\?])
'''
_TEST = {
2014-01-27 06:55:30 +00:00
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
'md5': 'a2ba71eebf523859fe527a61018f723e',
2014-01-27 06:55:30 +00:00
'info_dict': {
'id': '1012420',
'ext': 'mp4',
2014-01-27 06:55:30 +00:00
'title': 'Fun Jynx Maze solo',
'thumbnail': 're:^https?://.*\.jpg$',
'age_limit': 18,
2014-01-25 00:46:52 +00:00
}
2014-01-27 06:55:30 +00:00
}
2014-01-25 00:46:52 +00:00
def _real_extract(self, url):
2014-10-26 22:13:42 +00:00
video_id = self._match_id(url)
2014-01-25 00:46:52 +00:00
webpage = self._download_webpage(url, video_id)
video_title = self._search_regex(
r'mediaTitle = "([^"]+)"', webpage, 'title')
2014-01-27 11:39:39 +00:00
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)
2014-01-25 00:46:52 +00:00
formats = [{
'url': video_url,
'format_id': 'default-%s' % pl_c_qual,
2014-01-25 00:46:52 +00:00
}]
qualities_json = self._search_regex(
r'var pl_qualities\s*=\s*(.*?);\n', webpage, 'quality info')
qualities_data = json.loads(qualities_json)
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)
f = {
'format_id': quality_id,
'url': video_url,
'quality': i,
}
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'))
formats.append(f)
self._sort_formats(formats)
thumbnail = self._search_regex(
r"var\s+mov_thumb\s*=\s*'([^']+)';",
webpage, 'thumbnail', fatal=False)
2014-01-25 00:46:52 +00:00
return {
'id': video_id,
'title': video_title,
'formats': formats,
'age_limit': self._rta_search(webpage),
'thumbnail': thumbnail,
2014-01-25 00:46:52 +00:00
}