0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00

Merge remote-tracking branch 'sahutd/master'

This commit is contained in:
Jaime Marquínez Ferrándiz 2014-01-27 12:21:00 +01:00
commit 96d7b8873a
2 changed files with 41 additions and 0 deletions

View file

@ -47,6 +47,7 @@
from .dotsub import DotsubIE
from .dreisat import DreiSatIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .dropbox import DropboxIE
from .ebaumsworld import EbaumsWorldIE
from .ehow import EHowIE

View file

@ -0,0 +1,40 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
class DiscoveryIE(InfoExtractor):
_VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
_TEST = {
'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
'file': 'mission-impossible-outtakes.mp4',
'md5': 'e12614f9ee303a6ccef415cb0793eba2',
'info_dict': {
'title': 'MythBusters: Mission Impossible Outtakes'
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._search_regex(
r'(?<=\"name\": ")(?P<title>.*?)(?=\"\,)', webpage, r'Filename')
duration = int(self._search_regex(
r'(?<=\"duration\"\: )(?P<duration>.*?)(?=,)', webpage, r'Duration'))
formats_raw = self._search_regex(
r'(?<=\"mp4\":)(.*?)(}])', webpage, r'formats') + '}]'
formats_json = json.loads(formats_raw)
formats = []
for f in formats_json:
formats.append(
{'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])})
return {
'id': video_id,
'duration': duration,
'title': title,
'formats': formats
}