[pbs] Extract coveplayerid (Closes #3522)
This commit is contained in:
parent
c1d293cfa6
commit
4d9bd478f9
@ -20,17 +20,30 @@ class PBSIE(InfoExtractor):
|
|||||||
)
|
)
|
||||||
'''
|
'''
|
||||||
|
|
||||||
_TEST = {
|
_TESTS = [
|
||||||
'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
|
{
|
||||||
'md5': 'ce1888486f0908d555a8093cac9a7362',
|
'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
|
||||||
'info_dict': {
|
'md5': 'ce1888486f0908d555a8093cac9a7362',
|
||||||
'id': '2365006249',
|
'info_dict': {
|
||||||
'ext': 'mp4',
|
'id': '2365006249',
|
||||||
'title': 'A More Perfect Union',
|
'ext': 'mp4',
|
||||||
'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
|
'title': 'A More Perfect Union',
|
||||||
'duration': 3190,
|
'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
|
||||||
|
'duration': 3190,
|
||||||
|
},
|
||||||
},
|
},
|
||||||
}
|
{
|
||||||
|
'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
|
||||||
|
'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '2201174722',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist',
|
||||||
|
'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
|
||||||
|
'duration': 801,
|
||||||
|
},
|
||||||
|
},
|
||||||
|
]
|
||||||
|
|
||||||
def _extract_ids(self, url):
|
def _extract_ids(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
@ -40,10 +53,13 @@ class PBSIE(InfoExtractor):
|
|||||||
if presumptive_id:
|
if presumptive_id:
|
||||||
webpage = self._download_webpage(url, display_id)
|
webpage = self._download_webpage(url, display_id)
|
||||||
|
|
||||||
# frontline video embed
|
MEDIA_ID_REGEXES = [
|
||||||
|
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
|
||||||
|
r'class="coveplayerid">([^<]+)<', # coveplayer
|
||||||
|
]
|
||||||
|
|
||||||
media_id = self._search_regex(
|
media_id = self._search_regex(
|
||||||
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",
|
MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
|
||||||
webpage, 'frontline video ID', fatal=False, default=None)
|
|
||||||
if media_id:
|
if media_id:
|
||||||
return media_id, presumptive_id
|
return media_id, presumptive_id
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user