from __future__ import unicode_literals
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
compat_urllib_request,
)
+
class GDCVaultIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'
_TESTS = [
{
- u'url': u'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
- u'md5': u'7ce8388f544c88b7ac11c7ab1b593704',
- u'info_dict': {
- u"id": u"1019721",
- u"ext": u"mp4",
- u"title": u"Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)"
+ 'url': 'http://www.gdcvault.com/play/1019721/Doki-Doki-Universe-Sweet-Simple',
+ 'md5': '7ce8388f544c88b7ac11c7ab1b593704',
+ 'info_dict': {
+ 'id': '1019721',
+ 'ext': 'mp4',
+ 'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
}
},
{
- u'url': u'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
- u'md5': u'fca91078a90f28aa5164ef6b23b78654',
- u'info_dict': {
- u"id": u"1015683",
- u"ext": u"flv",
- u"title": u"Embracing the Dark Art of Mathematical Modeling in AI"
+ 'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
+ 'info_dict': {
+ 'id': '1015683',
+ 'ext': 'flv',
+ 'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
+ },
+ 'params': {
+ 'skip_download': True, # Requires rtmpdump
}
},
+ {
+ 'url': 'http://www.gdcvault.com/play/1015301/Thexder-Meets-Windows-95-or',
+ 'md5': 'a5eb77996ef82118afbbe8e48731b98e',
+ 'info_dict': {
+ 'id': '1015301',
+ 'ext': 'flv',
+ 'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
+ }
+ }
]
def _parse_mp4(self, xml_description):
akami_url = xml_description.find('./metadata/akamaiHost').text
slide_video_path = xml_description.find('./metadata/slideVideo').text
video_formats.append({
- 'url': 'rtmp://' + akami_url + '/' + slide_video_path,
- 'format_note': 'slide deck video',
- 'quality': -2,
- 'preference': -2,
- 'format_id': 'slides',
- })
+ 'url': 'rtmp://' + akami_url + '/' + slide_video_path,
+ 'format_note': 'slide deck video',
+ 'quality': -2,
+ 'preference': -2,
+ 'format_id': 'slides',
+ })
speaker_video_path = xml_description.find('./metadata/speakerVideo').text
video_formats.append({
- 'url': 'rtmp://' + akami_url + '/' + speaker_video_path,
- 'format_note': 'speaker video',
- 'quality': -1,
- 'preference': -1,
- 'format_id': 'speaker',
- })
+ 'url': 'rtmp://' + akami_url + '/' + speaker_video_path,
+ 'format_note': 'speaker video',
+ 'quality': -1,
+ 'preference': -1,
+ 'format_id': 'speaker',
+ })
return video_formats
def _login(self, webpage_url, video_id):
(username, password) = self._get_login_info()
if username is None or password is None:
- self.report_warning(u'It looks like ' + webpage_url + u' requires a login. Try specifying a username and password and try again.')
+ self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
return None
mobj = re.match(r'(?P<root_url>https?://.*?/).*', webpage_url)
request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- login_content = self._download_webpage(request, video_id, 'Logging in')
+ self._download_webpage(request, video_id, 'Logging in')
start_page = self._download_webpage(webpage_url, video_id, 'Getting authenticated video page')
- logout_content = self._download_webpage(logout_url, video_id, 'Logging out')
+ self._download_webpage(logout_url, video_id, 'Logging out')
return start_page
webpage_url = 'http://www.gdcvault.com/play/' + video_id
start_page = self._download_webpage(webpage_url, video_id)
- xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root', None, False)
+ direct_url = self._search_regex(
+ r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
+ start_page, 'url', default=None)
+ if direct_url:
+ video_url = 'http://www.gdcvault.com/' + direct_url
+ title = self._html_search_regex(
+ r'<td><strong>Session Name</strong></td>\s*<td>(.*?)</td>',
+ start_page, 'title')
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'ext': 'flv',
+ 'title': title,
+ }
+ xml_root = self._html_search_regex(
+ r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>',
+ start_page, 'xml root', default=None)
if xml_root is None:
# Probably need to authenticate
- start_page = self._login(webpage_url, video_id)
- if start_page is None:
- self.report_warning(u'Could not login.')
+ login_res = self._login(webpage_url, video_id)
+ if login_res is None:
+ self.report_warning('Could not login.')
else:
+ start_page = login_res
# Grab the url from the authenticated page
- xml_root = self._html_search_regex(r'<iframe src="(?P<xml_root>.*?)player.html.*?".*?</iframe>', start_page, 'xml root')
+ xml_root = self._html_search_regex(
+ r'<iframe src="(.*?)player.html.*?".*?</iframe>',
+ start_page, 'xml root')
- self.report_extraction(video_id)
- xml_name = self._html_search_regex(r'<iframe src=".*?\?xml=(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename', None, False)
+ xml_name = self._html_search_regex(
+ r'<iframe src=".*?\?xml=(.+?\.xml).*?".*?</iframe>',
+ start_page, 'xml filename', default=None)
if xml_name is None:
# Fallback to the older format
xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename')
xml_description = self._download_xml(xml_decription_url, video_id)
video_title = xml_description.find('./metadata/title').text
- video_details = {
- 'id': video_id,
- 'title': video_title,
- }
-
video_formats = self._parse_mp4(xml_description)
if video_formats is None:
video_formats = self._parse_flv(xml_description)
- return [{
+ return {
'id': video_id,
'title': video_title,
'formats': video_formats,
- }]
+ }
projects / youtube-dl / blobdiff