Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-10 06:17:16 +08:00
Code Issues Releases Wiki Activity

Fixed dailymotion video nd uploader extractor

Browse Source
This commit is contained in:
Laurent Raufaste 2011-05-29 12:36:12 -04:00
parent 4b0d9eed45
commit 368cb1fd0a
1 changed files with 14 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
youtube-dl
View File

@ -30,6 +30,7 @@ import time
import urllib import urllib
import urllib2 import urllib2
import zlib import zlib
import json
# parse_qs was moved from the cgi module to the urlparse module recently. # parse_qs was moved from the cgi module to the urlparse module recently.
try: try:
@ -1328,16 +1329,21 @@ class DailymotionIE(InfoExtractor):
return return
# Extract URL, uploader and title from webpage # Extract URL, uploader and title from webpage
# First we need to get the sequence urlencoded json variable
self.report_extraction(video_id) self.report_extraction(video_id)
mobj = re.search(r'(?i)addVariable\(\"video\"\s*,\s*\"([^\"]*)\"\)', webpage) mobj = re.search(r'(?i)addVariable\(\"sequence\"\s*,\s*\"([^\"]*)\"\)', webpage)
if mobj is None: if mobj is None:
self._downloader.trouble(u'ERROR: unable to extract media URL') self._downloader.trouble(u'ERROR: unable to extract media URL')
return return
mediaURL = urllib.unquote(mobj.group(1))
# if needed add http://www.dailymotion.com/ if relative URL # if needed add http://www.dailymotion.com/ if relative URL
sequenceJsonContent = urllib.unquote_plus(mobj.group(1))
video_url = mediaURL sequenceJson = json.loads(sequenceJsonContent)
try:
video_url = sequenceJson[0]["layerList"][0]["sequenceList"][1]["layerList"][2]["param"]["videoPluginParameters"]["hqURL"]
except:
self._downloader.trouble(u'ERROR: unable to extract media URL')
return
# '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>' # '<meta\s+name="title"\s+content="Dailymotion\s*[:\-]\s*(.*?)"\s*\/\s*>'
mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage) mobj = re.search(r'(?im)<title>Dailymotion\s*[\-:]\s*(.+?)</title>', webpage)
@ -1347,11 +1353,12 @@ class DailymotionIE(InfoExtractor):
video_title = mobj.group(1).decode('utf-8') video_title = mobj.group(1).decode('utf-8')
video_title = sanitize_title(video_title) video_title = sanitize_title(video_title)
mobj = re.search(r'(?im)<Attribute name="owner">(.+?)</Attribute>', webpage) # Extract the video uploader nickname from the sequence JSON
if mobj is None: try:
video_uploader = sequenceJson[0]["layerList"][0]["sequenceList"][1]["layerList"][0]["param"]["metadata"]["uploader"]
except:
self._downloader.trouble(u'ERROR: unable to extract uploader nickname') self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
return return
video_uploader = mobj.group(1)
try: try:
# Process video information # Process video information