[ministrygrid] Add extractor (Fixes #2900)

This commit is contained in:
Philipp Hagemeister 2014-08-24 04:47:18 +02:00
parent 54036b3991
commit 4d54ef20a2
3 changed files with 70 additions and 1 deletions

View file

@ -184,6 +184,7 @@ from .malemotion import MalemotionIE
from .mdr import MDRIE from .mdr import MDRIE
from .metacafe import MetacafeIE from .metacafe import MetacafeIE
from .metacritic import MetacriticIE from .metacritic import MetacriticIE
from .ministrygrid import MinistryGridIE
from .mit import TechTVMITIE, MITIE, OCWMITIE from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mitele import MiTeleIE from .mitele import MiTeleIE
from .mixcloud import MixcloudIE from .mixcloud import MixcloudIE

View file

@ -22,6 +22,7 @@ from ..utils import (
smuggle_url, smuggle_url,
unescapeHTML, unescapeHTML,
unified_strdate, unified_strdate,
unsmuggle_url,
url_basename, url_basename,
) )
from .brightcove import BrightcoveIE from .brightcove import BrightcoveIE
@ -487,7 +488,14 @@ class GenericIE(InfoExtractor):
else: else:
assert ':' in default_search assert ':' in default_search
return self.url_result(default_search + url) return self.url_result(default_search + url)
video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
url, smuggled_data = unsmuggle_url(url)
force_videoid = None
if smuggled_data and 'force_videoid' in smuggled_data:
force_videoid = smuggled_data['force_videoid']
video_id = force_videoid
else:
video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0]
self.to_screen('%s: Requesting header' % video_id) self.to_screen('%s: Requesting header' % video_id)
@ -498,6 +506,9 @@ class GenericIE(InfoExtractor):
new_url = response.geturl() new_url = response.geturl()
if url != new_url: if url != new_url:
self.report_following_redirect(new_url) self.report_following_redirect(new_url)
if force_videoid:
new_url = smuggle_url(
new_url, {'force_videoid': force_videoid})
return self.url_result(new_url) return self.url_result(new_url)
# Check for direct link to a video # Check for direct link to a video

View file

@ -0,0 +1,57 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
smuggle_url,
)
class MinistryGridIE(InfoExtractor):
_VALID_URL = r'https?://www\.ministrygrid.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
_TEST = {
'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers',
'md5': '844be0d2a1340422759c2a9101bab017',
'info_dict': {
'id': '3453494717001',
'ext': 'mp4',
'title': 'The Gospel by Numbers',
'description': 'Coming soon from T4G 2014!',
'uploader': 'LifeWay Christian Resources (MG)',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
portlets_json = self._search_regex(
r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list')
portlets = json.loads(portlets_json)
pl_id = self._search_regex(
r'<!--\s*p_l_id - ([0-9]+)<br>', webpage, 'p_l_id')
for i, portlet in enumerate(portlets):
portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet)
portlet_code = self._download_webpage(
portlet_url, video_id,
note='Looking in portlet %s (%d/%d)' % (portlet, i + 1, len(portlets)),
fatal=False)
video_iframe_url = self._search_regex(
r'<iframe.*?src="([^"]+)"', portlet_code, 'video iframe',
default=None)
if video_iframe_url:
surl = smuggle_url(
video_iframe_url, {'force_videoid': video_id})
return {
'_type': 'url',
'id': video_id,
'url': surl,
}
raise ExtractorError('Could not find video iframe in any portlets')