from __future__ import unicode_literals
+import json
import re
-import string
from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
-)
-
-translation_table = (
- '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12'
- '\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#:%.\'=)*+,-./0123'
- '456789:;</>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]&_`hbcevofhdjknamoutsstupwrli{'
- '|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f'
- '\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1'
- '\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3'
- '\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5'
- '\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7'
- '\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9'
- '\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb'
- '\xfc\xfd\xfe\xff'
-)
+
+
+_translation_table = {
+ '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',
+ '$': ':', '&': '.', '(': '=', '^': '&', '=': '/',
+}
+
+
+def _decode(s):
+ return ''.join(_translation_table.get(c, c) for c in s)
class CliphunterIE(InfoExtractor):
IE_NAME = 'cliphunter'
- _VALID_URL = (r'(?:http://)?(?:www\.)?cliphunter\.com/w/'
- '(?P<id>[0-9]+)/'
- '(?P<seo>.+?)(?:\?.*)?')
- _TESTS = {
+ _VALID_URL = r'''(?x)http://(?:www\.)?cliphunter\.com/w/
+ (?P<id>[0-9]+)/
+ (?P<seo>.+?)(?:$|[#\?])
+ '''
+ _TEST = {
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
- 'file': '1012420.flv',
- 'md5': '15e7740f30428abf70f4223478dc1225',
+ 'md5': 'a2ba71eebf523859fe527a61018f723e',
'info_dict': {
+ 'id': '1012420',
+ 'ext': 'mp4',
'title': 'Fun Jynx Maze solo',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'age_limit': 18,
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
+ video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- 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_title = self._search_regex(r'mediaTitle = "([^"]+)"', webpage, 'title')
-
- video_url = string.translate(pl_fiji.encode(), translation_table)
+ 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': pl_c_qual,
- 'format_id': pl_c_qual,
+ 'format_id': 'default-%s' % pl_c_qual,
}]
+ 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)
+
return {
'id': video_id,
'title': video_title,
'formats': formats,
+ 'age_limit': self._rta_search(webpage),
+ 'thumbnail': thumbnail,
}