X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/87a0165ca7e39af4dacb7ec637063b2cd35ae40b..7b550e005da7fd498cfbf1b7c04b05e5540eb6fc:/youtube_dl/extractor/brightcove.py
diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py
index 945cf19..465ae39 100644
--- a/youtube_dl/extractor/brightcove.py
+++ b/youtube_dl/extractor/brightcove.py
@@ -1,10 +1,13 @@
# coding: utf-8
from __future__ import unicode_literals
-import re
+import base64
import json
+import re
+import struct
from .common import InfoExtractor
+from .adobepass import AdobePassIE
from ..compat import (
compat_etree_fromstring,
compat_parse_qs,
@@ -17,6 +20,7 @@ from ..compat import (
from ..utils import (
determine_ext,
ExtractorError,
+ extract_attributes,
find_xpath_attr,
fix_xml_ampersands,
float_or_none,
@@ -109,6 +113,7 @@ class BrightcoveLegacyIE(InfoExtractor):
'upload_date': '20140827',
'uploader_id': '710858724001',
},
+ 'skip': 'Video gone',
},
{
# playlist with 'videoList'
@@ -129,6 +134,12 @@ class BrightcoveLegacyIE(InfoExtractor):
},
'playlist_mincount': 10,
},
+ {
+ # playerID inferred from bcpid
+ # from http://www.un.org/chinese/News/story.asp?NewsID=27724
+ 'url': 'https://link.brightcove.com/services/player/bcpid1722935254001/?bctid=5360463607001&autoStart=false&secureConnections=true&width=650&height=350',
+ 'only_matching': True, # Tested in GenericIE
+ }
]
FLV_VCODECS = {
1: 'SORENSON',
@@ -179,7 +190,7 @@ class BrightcoveLegacyIE(InfoExtractor):
params = {}
- playerID = find_param('playerID')
+ playerID = find_param('playerID') or find_param('playerId')
if playerID is None:
raise ExtractorError('Cannot find player ID')
params['playerID'] = playerID
@@ -191,6 +202,16 @@ class BrightcoveLegacyIE(InfoExtractor):
# These fields hold the id of the video
videoPlayer = find_param('@videoPlayer') or find_param('videoId') or find_param('videoID') or find_param('@videoList')
if videoPlayer is not None:
+ if isinstance(videoPlayer, list):
+ videoPlayer = videoPlayer[0]
+ videoPlayer = videoPlayer.strip()
+ # UUID is also possible for videoPlayer (e.g.
+ # http://www.popcornflix.com/hoodies-vs-hooligans/7f2d2b87-bbf2-4623-acfb-ea942b4f01dd
+ # or http://www8.hp.com/cn/zh/home.html)
+ if not (re.match(
+ r'^(?:\d+|[\da-fA-F]{8}-?[\da-fA-F]{4}-?[\da-fA-F]{4}-?[\da-fA-F]{4}-?[\da-fA-F]{12})$',
+ videoPlayer) or videoPlayer.startswith('ref:')):
+ return None
params['@videoPlayer'] = videoPlayer
linkBase = find_param('linkBaseURL')
if linkBase is not None:
@@ -204,7 +225,7 @@ class BrightcoveLegacyIE(InfoExtractor):
# // build Brightcove XML
# }
m = re.search(
- r'''(?x)customBC.\createVideo\(
+ r'''(?x)customBC\.createVideo\(
.*? # skipping width and height
["\'](?P\d+)["\']\s*,\s* # playerID
["\'](?PAQ[^"\']{48})[^"\']*["\']\s*,\s* # playerKey begins with AQ and is 50 characters
@@ -232,13 +253,16 @@ class BrightcoveLegacyIE(InfoExtractor):
"""Return a list of all Brightcove URLs from the webpage """
url_m = re.search(
- r']+
+ content=([\'"])(?Phttps?://(?:secure|c)\.brightcove.com/(?:(?!\2).)+)\2
+ ''', webpage)
if url_m:
- url = unescapeHTML(url_m.group(1))
+ url = unescapeHTML(url_m.group('url'))
# Some sites don't add it, we can't download with this url, for example:
# http://www.ktvu.com/videos/news/raw-video-caltrain-releases-video-of-man-almost/vCTZdY/
- if 'playerKey' in url or 'videoId' in url:
+ if 'playerKey' in url or 'videoId' in url or 'idVideo' in url:
return [url]
matches = re.findall(
@@ -251,15 +275,19 @@ class BrightcoveLegacyIE(InfoExtractor):
if matches:
return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
- return list(filter(None, [
- cls._build_brighcove_url_from_js(custom_bc)
- for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)]))
+ matches = re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)
+ if matches:
+ return list(filter(None, [
+ cls._build_brighcove_url_from_js(custom_bc)
+ for custom_bc in matches]))
+ return [src for _, src in re.findall(
+ r'