Browse Source

Merge pull request #3690 from naglis/sharesix

[sharesix] Add new extractor
totalwebcasting
Sergey M. 10 years ago
parent
commit
9face18d08
2 changed files with 92 additions and 0 deletions
  1. +1
    -0
      youtube_dl/extractor/__init__.py
  2. +91
    -0
      youtube_dl/extractor/sharesix.py

+ 1
- 0
youtube_dl/extractor/__init__.py View File

@ -297,6 +297,7 @@ from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .servingsys import ServingSysIE
from .shared import SharedIE
from .sharesix import ShareSixIE
from .sina import SinaIE
from .slideshare import SlideshareIE
from .slutload import SlutloadIE


+ 91
- 0
youtube_dl/extractor/sharesix.py View File

@ -0,0 +1,91 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
compat_urllib_request,
parse_duration,
)
class ShareSixIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sharesix\.com/(?:f/)?(?P<id>[0-9a-zA-Z]+)'
_TESTS = [
{
'url': 'http://sharesix.com/f/OXjQ7Y6',
'md5': '9e8e95d8823942815a7d7c773110cc93',
'info_dict': {
'id': 'OXjQ7Y6',
'ext': 'mp4',
'title': 'big_buck_bunny_480p_surround-fix.avi',
'duration': 596,
'width': 854,
'height': 480,
},
},
{
'url': 'http://sharesix.com/lfrwoxp35zdd',
'md5': 'dd19f1435b7cec2d7912c64beeee8185',
'info_dict': {
'id': 'lfrwoxp35zdd',
'ext': 'flv',
'title': 'WhiteBoard___a_Mac_vs_PC_Parody_Cartoon.mp4.flv',
'duration': 65,
'width': 1280,
'height': 720,
},
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
fields = {
'method_free': 'Free'
}
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(req, video_id,
'Downloading video page')
video_url = self._search_regex(
r"var\slnk1\s=\s'([^']+)'", webpage, 'video URL')
title = self._html_search_regex(
r'(?s)<dt>Filename:</dt>.+?<dd>(.+?)</dd>', webpage, 'title')
duration = parse_duration(
self._search_regex(
r'(?s)<dt>Length:</dt>.+?<dd>(.+?)</dd>',
webpage,
'duration',
fatal=False
)
)
m = re.search(
r'''(?xs)<dt>Width\sx\sHeight</dt>.+?
<dd>(?P<width>\d+)\sx\s(?P<height>\d+)</dd>''',
webpage
)
width = height = None
if m:
width, height = int(m.group('width')), int(m.group('height'))
formats = [{
'format_id': 'sd',
'url': video_url,
'width': width,
'height': height,
}]
return {
'id': video_id,
'title': title,
'duration': duration,
'formats': formats,
}

Loading…
Cancel
Save