about summary refs log tree commit diff
path: root/youtube_dl/extractor/pbs.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2015-11-07 00:39:16 +0600
committerSergey M․ <dstftw@gmail.com>2015-11-07 00:39:16 +0600
commit686f98816ecbbcb224d1336682688b05cdb051a6 (patch)
tree125d3f3ea63747e13851fd4d3a1205ad0b742421 /youtube_dl/extractor/pbs.py
parent0fa6b17dccd2347cb0611651fc04e36839d33a4e (diff)
downloadyoutube-dl-686f98816ecbbcb224d1336682688b05cdb051a6.tar.gz
youtube-dl-686f98816ecbbcb224d1336682688b05cdb051a6.tar.xz
youtube-dl-686f98816ecbbcb224d1336682688b05cdb051a6.zip
[pbs] Add support for flp frontlines (Closes #7369)
Diffstat (limited to 'youtube_dl/extractor/pbs.py')
-rw-r--r--youtube_dl/extractor/pbs.py18
1 files changed, 18 insertions, 0 deletions
diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 7b868d057..3169e9c3f 100644
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -8,6 +8,7 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     int_or_none,
+    strip_jsonp,
     unified_strdate,
     US_RATINGS,
 )
@@ -191,6 +192,23 @@ class PBSIE(InfoExtractor):
             if media_id:
                 return media_id, presumptive_id, upload_date
 
+            # Fronline video embedded via flp
+            video_id = self._search_regex(
+                r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')
+            if video_id:
+                # pkg_id calculation is reverse engineered from
+                # http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js
+                prg_id = self._search_regex(
+                    r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')[7:]
+                if 'q' in prg_id:
+                    prg_id = prg_id.split('q')[1]
+                prg_id = int(prg_id, 16)
+                getdir = self._download_json(
+                    'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
+                    presumptive_id, 'Downloading getdir JSON',
+                    transform_source=strip_jsonp)
+                return getdir['mid'], presumptive_id, upload_date
+
             for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
                 url = self._search_regex(
                     r'src=(["\'])(?P<url>.+?partnerplayer.+?)\1', iframe,