[expotv] Add new extractor (Fixes #3552)

This commit is contained in:
Philipp Hagemeister 2014-08-24 06:41:55 +02:00
parent 51ed9fce09
commit 423817c468
3 changed files with 75 additions and 0 deletions

View file

@ -88,6 +88,7 @@ from .engadget import EngadgetIE
from .escapist import EscapistIE from .escapist import EscapistIE
from .everyonesmixtape import EveryonesMixtapeIE from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE from .exfm import ExfmIE
from .expotv import ExpoTVIE
from .extremetube import ExtremeTubeIE from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE from .facebook import FacebookIE
from .faz import FazIE from .faz import FazIE

View file

@ -0,0 +1,73 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_strdate,
)
class ExpoTVIE(InfoExtractor):
_VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
_TEST = {
'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561',
'md5': '2985e6d7a392b2f7a05e0ca350fe41d0',
'info_dict': {
'id': '17561',
'ext': 'mp4',
'upload_date': '20060212',
'title': 'My Favorite Online Scrapbook Store',
'view_count': int,
'description': 'You\'ll find most everything you need at this virtual store front.',
'uploader': 'Anna T.',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
player_key = self._search_regex(
r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
config_url = 'http://client.expotv.com/video/config/%s/%s' % (
video_id, player_key)
config = self._download_json(
config_url, video_id,
note='Downloading video configuration')
formats = [{
'url': fcfg['file'],
'height': int_or_none(fcfg.get('height')),
'format_note': fcfg.get('label'),
'ext': self._search_regex(
r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'],
'file extension', default=None),
} for fcfg in config['sources']]
self._sort_formats(formats)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = config.get('image')
view_count = int_or_none(self._search_regex(
r'<h5>Plays: ([0-9]+)</h5>', webpage, 'view counts'))
uploader = self._search_regex(
r'<div class="reviewer">\s*<img alt="([^"]+)"', webpage, 'uploader',
fatal=False)
upload_date = unified_strdate(self._search_regex(
r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
fatal=False))
return {
'id': video_id,
'formats': formats,
'title': title,
'description': description,
'view_count': view_count,
'thumbnail': thumbnail,
'uploader': uploader,
'upload_date': upload_date,
}

View file

@ -855,6 +855,7 @@ def unified_strdate(date_str):
'%Y/%m/%d', '%Y/%m/%d',
'%d.%m.%Y', '%d.%m.%Y',
'%d/%m/%Y', '%d/%m/%Y',
'%d/%m/%y',
'%Y/%m/%d %H:%M:%S', '%Y/%m/%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S', '%Y-%m-%d %H:%M:%S',
'%d.%m.%Y %H:%M', '%d.%m.%Y %H:%M',