pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-14 06:18:00 +09:00
Code Issues Projects Releases Wiki Activity

[infoq] Simplify and use unicode_literals

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-01-29 15:34:35 +01:00
parent d4a21e0b49
commit d882161d5a
1 changed files with 16 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
youtube_dl/extractor/infoq.py
View File

@ -1,27 +1,27 @@
from __future__ import unicode_literals
import base64
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
ExtractorError,
)
class InfoQIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
_TEST = {
u"name": u"InfoQ",
u"url": u"http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
u"file": u"12-jan-pythonthings.mp4",
u"info_dict": {
u"description": u"Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
u"title": u"A Few of My Favorite [Python] Things"
"name": "InfoQ",
"url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
"file": "12-jan-pythonthings.mp4",
"info_dict": {
"description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
"title": "A Few of My Favorite [Python] Things",
},
"params": {
"skip_download": True,
},
u"params": {
u"skip_download": True
}
}
def _real_extract(self, url):
@ -31,32 +31,25 @@ class InfoQIE(InfoExtractor):
self.report_extraction(url)
# Extract video URL
mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
if mobj is None:
raise ExtractorError(u'Unable to extract video url')
real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
encoded_id = self._search_regex(r"jsclassref ?= ?'([^']*)'", webpage, 'encoded id')
real_id = compat_urllib_parse.unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8'))
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
# Extract title
video_title = self._search_regex(r'contentTitle = "(.*?)";',
webpage, u'title')
webpage, 'title')
# Extract description
video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
webpage, u'description', fatal=False)
webpage, 'description', fatal=False)
video_filename = video_url.split('/')[-1]
video_id, extension = video_filename.split('.')
info = {
return {
'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': None,
'title': video_title,
'ext': extension, # Extension is always(?) mp4, but seems to be flv
'thumbnail': None,
'description': video_description,
}
return [info]