[tudou] Extract player URL from the webpage
This commit is contained in:
parent
c71a3195af
commit
238755752f
|
@ -56,6 +56,10 @@ class TudouIE(InfoExtractor):
|
||||||
thumbnail_url = self._search_regex(
|
thumbnail_url = self._search_regex(
|
||||||
r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False)
|
r",pic:\s*[\"'](.+?)[\"']", webpage, 'thumbnail URL', fatal=False)
|
||||||
|
|
||||||
|
player_url = self._search_regex(
|
||||||
|
r"playerUrl\s*:\s*['\"](.+?\.swf)[\"']",
|
||||||
|
webpage, 'player URL', default=self._PLAYER_URL)
|
||||||
|
|
||||||
segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments')
|
segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments')
|
||||||
segments = json.loads(segs_json)
|
segments = json.loads(segs_json)
|
||||||
# It looks like the keys are the arguments that have to be passed as
|
# It looks like the keys are the arguments that have to be passed as
|
||||||
|
@ -79,7 +83,7 @@ class TudouIE(InfoExtractor):
|
||||||
'title': title,
|
'title': title,
|
||||||
'thumbnail': thumbnail_url,
|
'thumbnail': thumbnail_url,
|
||||||
'http_headers': {
|
'http_headers': {
|
||||||
'Referer': self._PLAYER_URL,
|
'Referer': player_url,
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
result.append(part_info)
|
result.append(part_info)
|
||||||
|
|
Loading…
Reference in New Issue