[wistia] Use API and make more generic

This commit is contained in:
Naglis Jonaitis 2014-09-20 03:02:11 +03:00
parent 532f5bff70
commit 746c67d72f
2 changed files with 32 additions and 6 deletions

View File

@ -382,6 +382,19 @@ class GenericIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$',
},
},
# Wistia embed
{
'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson',
'md5': '8788b683c777a5cf25621eaf286d0c23',
'info_dict': {
'id': '1cfaf6b7ea',
'ext': 'mov',
'title': 'md5:51364a8d3d009997ba99656004b5e20d',
'duration': 643.0,
'filesize': 182808282,
'uploader': 'education-portal.com',
},
},
]
def report_download_webpage(self, video_id):
@ -654,6 +667,16 @@ def _playlist_from_matches(matches, getter, ie=None):
'title': video_title,
'id': video_id,
}
match = re.search(r'(?:id=["\']wistia_|data-wistiaid=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
if match:
return {
'_type': 'url_transparent',
'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')),
'ie_key': 'Wistia',
'uploader': video_uploader,
'title': video_title,
'id': match.group('id')
}
# Look for embedded blip.tv player
mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)

View File

@ -1,13 +1,14 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import ExtractorError, compat_urllib_request
class WistiaIE(InfoExtractor):
_VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
_API_URL = 'http://fast.wistia.com/embed/medias/{0:}.json'
_TEST = {
'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt',
@ -24,11 +25,13 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
data_json = self._html_search_regex(
r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data')
data = json.loads(data_json)
request = compat_urllib_request.Request(self._API_URL.format(video_id))
request.add_header('Referer', url) # Some videos require this.
data_json = self._download_json(request, video_id)
if data_json.get('error'):
raise ExtractorError('Error while getting the playlist',
expected=True)
data = data_json['media']
formats = []
thumbnails = []