[ministrygrid] Add extractor (Fixes #2900)

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 52354e6e0e261d018ab4ee92b57306c998ea8741..9dccbb8ed41e8e5cf7d3e4c6fc31339f09f484ec 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -184,6 +184,7 @@ from .malemotion import MalemotionIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE
 from .mdr import MDRIE
 from .metacafe import MetacafeIE
 from .metacritic import MetacriticIE

+from .ministrygrid import MinistryGridIE

 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE
 from .mit import TechTVMITIE, MITIE, OCWMITIE
 from .mitele import MiTeleIE
 from .mixcloud import MixcloudIE

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index 8b2d1d033ab2f260e49b18c8ecc7d1d3fc695eaf..7fce564c60895b059deaa437912c3eb9325107b8 100644 (file)
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -22,6 +22,7 @@ from ..utils import (
     smuggle_url,
     unescapeHTML,
     unified_strdate,
     smuggle_url,
     unescapeHTML,
     unified_strdate,

+    unsmuggle_url,

     url_basename,
 )
 from .brightcove import BrightcoveIE
     url_basename,
 )
 from .brightcove import BrightcoveIE


@@ -487,7 +488,14 @@ class GenericIE(InfoExtractor):
             else:
                 assert ':' in default_search
                 return self.url_result(default_search + url)
             else:
                 assert ':' in default_search
                 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()
             if url != new_url:
                 self.report_following_redirect(new_url)
             new_url = response.geturl()
             if url != 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)
 
             # Check for direct link to a video
                 return self.url_result(new_url)
 
             # Check for direct link to a video

diff --git a/youtube_dl/extractor/ministrygrid.py b/youtube_dl/extractor/ministrygrid.py
new file mode 100644 (file)
index 0000000..949ad11
--- /dev/null
+++ b/youtube_dl/extractor/ministrygrid.py
@@ -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')