jon1scr
/
yt-dlc
forked from minhngoc25a/yt-dlc
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[cliphunter] Simplify

This commit is contained in:
Philipp Hagemeister 2014-01-27 07:55:30 +01:00
parent 5ab772f09c
commit efc867775e
1 changed files with 13 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
youtube_dl/extractor/cliphunter.py
View File

@ -1,9 +1,10 @@
from __future__ import unicode_literals
import re import re
import string import string
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext,
ExtractorError, ExtractorError,
) )
@ -23,39 +24,34 @@ translation_table = (
class CliphunterIE(InfoExtractor): class CliphunterIE(InfoExtractor):
"""Information Extractor for Cliphunter""" IE_NAME = 'cliphunter'
IE_NAME = u'cliphunter'
_VALID_URL = (r'(?:http://)?(?:www\.)?cliphunter\.com/w/' _VALID_URL = (r'(?:http://)?(?:www\.)?cliphunter\.com/w/'
'(?P<id>[0-9]+)/' '(?P<id>[0-9]+)/'
'(?P<seo>.+?)(?:\?.*)?') '(?P<seo>.+?)(?:\?.*)?')
_TESTS = [{ _TESTS = {
u'url': u'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo', 'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
u'file': u'1012420.flv', 'file': '1012420.flv',
u'md5': u'15e7740f30428abf70f4223478dc1225', 'md5': '15e7740f30428abf70f4223478dc1225',
u'info_dict': { 'info_dict': {
u'title': u'Fun Jynx Maze solo', 'title': 'Fun Jynx Maze solo',
} }
}] }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
if mobj is None:
raise ExtractorError(u'Unable to extract media URL')
video_id = mobj.group('id') video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
pl_fiji = re.search(r'pl_fiji = \'([^\']+)\'', webpage).group(1) pl_fiji = self._search_regex(r'pl_fiji = \'([^\']+)\'', webpage, 'video data')
pl_c_qual = re.search(r'pl_c_qual = "(.)"', webpage).group(1) pl_c_qual = self._search_regex(r'pl_c_qual = "(.)"', webpage, 'video quality')
video_title = re.search(r'mediaTitle = "([^"]+)"', webpage).group(1) video_title = self._search_regex(r'mediaTitle = "([^"]+)"', webpage, 'title')
video_url = string.translate(pl_fiji.encode(), translation_table) video_url = string.translate(pl_fiji.encode(), translation_table)
formats = [{ formats = [{
'url': video_url, 'url': video_url,
'ext': determine_ext(video_url),
'format': pl_c_qual, 'format': pl_c_qual,
'format_id': pl_c_qual, 'format_id': pl_c_qual,
}] }]