mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-29 13:42:37 +00:00
Move StanfordOC IE into its own file
This commit is contained in:
Philipp Hagemeister
parent
fda7d31aa0
commit
291a168bcc
2 changed files with 113 additions and 95 deletions
|
|
@ -37,6 +37,7 @@ from .extractor.myvideo import MyVideoIE
|
||||||
from .extractor.statigram import StatigramIE
|
from .extractor.statigram import StatigramIE
|
||||||
from .extractor.photobucket import PhotobucketIE
|
from .extractor.photobucket import PhotobucketIE
|
||||||
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
|
from .extractor.soundcloud import SoundcloudIE, SoundcloudSetIE
|
||||||
|
from .extractor.stanfordoc import StanfordOpenClassroomIE
|
||||||
from .extractor.vimeo import VimeoIE
|
from .extractor.vimeo import VimeoIE
|
||||||
from .extractor.xvideos import XVideosIE
|
from .extractor.xvideos import XVideosIE
|
||||||
from .extractor.yahoo import YahooIE, YahooSearchIE
|
from .extractor.yahoo import YahooIE, YahooSearchIE
|
||||||
|
|
@ -150,101 +151,6 @@ class MixcloudIE(InfoExtractor):
|
||||||
'player_url': player_url.decode('utf-8'),
|
'player_url': player_url.decode('utf-8'),
|
||||||
}]
|
}]
|
||||||
|
|
||||||
class StanfordOpenClassroomIE(InfoExtractor):
|
|
||||||
"""Information extractor for Stanford's Open ClassRoom"""
|
|
||||||
|
|
||||||
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
|
|
||||||
IE_NAME = u'stanfordoc'
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
mobj = re.match(self._VALID_URL, url)
|
|
||||||
if mobj is None:
|
|
||||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
|
||||||
|
|
||||||
if mobj.group('course') and mobj.group('video'): # A specific video
|
|
||||||
course = mobj.group('course')
|
|
||||||
video = mobj.group('video')
|
|
||||||
info = {
|
|
||||||
'id': course + '_' + video,
|
|
||||||
'uploader': None,
|
|
||||||
'upload_date': None,
|
|
||||||
}
|
|
||||||
|
|
||||||
self.report_extraction(info['id'])
|
|
||||||
baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
|
|
||||||
xmlUrl = baseUrl + video + '.xml'
|
|
||||||
try:
|
|
||||||
metaXml = compat_urllib_request.urlopen(xmlUrl).read()
|
|
||||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
|
||||||
raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
|
|
||||||
mdoc = xml.etree.ElementTree.fromstring(metaXml)
|
|
||||||
try:
|
|
||||||
info['title'] = mdoc.findall('./title')[0].text
|
|
||||||
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
|
|
||||||
except IndexError:
|
|
||||||
raise ExtractorError(u'Invalid metadata XML file')
|
|
||||||
info['ext'] = info['url'].rpartition('.')[2]
|
|
||||||
return [info]
|
|
||||||
elif mobj.group('course'): # A course page
|
|
||||||
course = mobj.group('course')
|
|
||||||
info = {
|
|
||||||
'id': course,
|
|
||||||
'type': 'playlist',
|
|
||||||
'uploader': None,
|
|
||||||
'upload_date': None,
|
|
||||||
}
|
|
||||||
|
|
||||||
coursepage = self._download_webpage(url, info['id'],
|
|
||||||
note='Downloading course info page',
|
|
||||||
errnote='Unable to download course info page')
|
|
||||||
|
|
||||||
info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
|
|
||||||
|
|
||||||
info['description'] = self._html_search_regex('<description>([^<]+)</description>',
|
|
||||||
coursepage, u'description', fatal=False)
|
|
||||||
|
|
||||||
links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
|
|
||||||
info['list'] = [
|
|
||||||
{
|
|
||||||
'type': 'reference',
|
|
||||||
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
|
|
||||||
}
|
|
||||||
for vpage in links]
|
|
||||||
results = []
|
|
||||||
for entry in info['list']:
|
|
||||||
assert entry['type'] == 'reference'
|
|
||||||
results += self.extract(entry['url'])
|
|
||||||
return results
|
|
||||||
else: # Root page
|
|
||||||
info = {
|
|
||||||
'id': 'Stanford OpenClassroom',
|
|
||||||
'type': 'playlist',
|
|
||||||
'uploader': None,
|
|
||||||
'upload_date': None,
|
|
||||||
}
|
|
||||||
|
|
||||||
self.report_download_webpage(info['id'])
|
|
||||||
rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
|
|
||||||
try:
|
|
||||||
rootpage = compat_urllib_request.urlopen(rootURL).read()
|
|
||||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
|
||||||
raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
|
|
||||||
|
|
||||||
info['title'] = info['id']
|
|
||||||
|
|
||||||
links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
|
|
||||||
info['list'] = [
|
|
||||||
{
|
|
||||||
'type': 'reference',
|
|
||||||
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
|
|
||||||
}
|
|
||||||
for cpage in links]
|
|
||||||
|
|
||||||
results = []
|
|
||||||
for entry in info['list']:
|
|
||||||
assert entry['type'] == 'reference'
|
|
||||||
results += self.extract(entry['url'])
|
|
||||||
return results
|
|
||||||
|
|
||||||
class MTVIE(InfoExtractor):
|
class MTVIE(InfoExtractor):
|
||||||
"""Information extractor for MTV.com"""
|
"""Information extractor for MTV.com"""
|
||||||
|
|
|
||||||
112
youtube_dl/extractor/stanfordoc.py
Normal file
112
youtube_dl/extractor/stanfordoc.py
Normal file
|
|
@ -0,0 +1,112 @@
|
||||||
|
import re
|
||||||
|
import socket
|
||||||
|
import xml.etree.ElementTree
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
compat_http_client,
|
||||||
|
compat_str,
|
||||||
|
compat_urllib_error,
|
||||||
|
compat_urllib_request,
|
||||||
|
|
||||||
|
ExtractorError,
|
||||||
|
orderedSet,
|
||||||
|
unescapeHTML,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class StanfordOpenClassroomIE(InfoExtractor):
|
||||||
|
"""Information extractor for Stanford's Open ClassRoom"""
|
||||||
|
|
||||||
|
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
|
||||||
|
IE_NAME = u'stanfordoc'
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
if mobj is None:
|
||||||
|
raise ExtractorError(u'Invalid URL: %s' % url)
|
||||||
|
|
||||||
|
if mobj.group('course') and mobj.group('video'): # A specific video
|
||||||
|
course = mobj.group('course')
|
||||||
|
video = mobj.group('video')
|
||||||
|
info = {
|
||||||
|
'id': course + '_' + video,
|
||||||
|
'uploader': None,
|
||||||
|
'upload_date': None,
|
||||||
|
}
|
||||||
|
|
||||||
|
self.report_extraction(info['id'])
|
||||||
|
baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/'
|
||||||
|
xmlUrl = baseUrl + video + '.xml'
|
||||||
|
try:
|
||||||
|
metaXml = compat_urllib_request.urlopen(xmlUrl).read()
|
||||||
|
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||||
|
raise ExtractorError(u'Unable to download video info XML: %s' % compat_str(err))
|
||||||
|
mdoc = xml.etree.ElementTree.fromstring(metaXml)
|
||||||
|
try:
|
||||||
|
info['title'] = mdoc.findall('./title')[0].text
|
||||||
|
info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text
|
||||||
|
except IndexError:
|
||||||
|
raise ExtractorError(u'Invalid metadata XML file')
|
||||||
|
info['ext'] = info['url'].rpartition('.')[2]
|
||||||
|
return [info]
|
||||||
|
elif mobj.group('course'): # A course page
|
||||||
|
course = mobj.group('course')
|
||||||
|
info = {
|
||||||
|
'id': course,
|
||||||
|
'type': 'playlist',
|
||||||
|
'uploader': None,
|
||||||
|
'upload_date': None,
|
||||||
|
}
|
||||||
|
|
||||||
|
coursepage = self._download_webpage(url, info['id'],
|
||||||
|
note='Downloading course info page',
|
||||||
|
errnote='Unable to download course info page')
|
||||||
|
|
||||||
|
info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id'])
|
||||||
|
|
||||||
|
info['description'] = self._html_search_regex('<description>([^<]+)</description>',
|
||||||
|
coursepage, u'description', fatal=False)
|
||||||
|
|
||||||
|
links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
|
||||||
|
info['list'] = [
|
||||||
|
{
|
||||||
|
'type': 'reference',
|
||||||
|
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage),
|
||||||
|
}
|
||||||
|
for vpage in links]
|
||||||
|
results = []
|
||||||
|
for entry in info['list']:
|
||||||
|
assert entry['type'] == 'reference'
|
||||||
|
results += self.extract(entry['url'])
|
||||||
|
return results
|
||||||
|
else: # Root page
|
||||||
|
info = {
|
||||||
|
'id': 'Stanford OpenClassroom',
|
||||||
|
'type': 'playlist',
|
||||||
|
'uploader': None,
|
||||||
|
'upload_date': None,
|
||||||
|
}
|
||||||
|
|
||||||
|
self.report_download_webpage(info['id'])
|
||||||
|
rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php'
|
||||||
|
try:
|
||||||
|
rootpage = compat_urllib_request.urlopen(rootURL).read()
|
||||||
|
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||||
|
raise ExtractorError(u'Unable to download course info page: ' + compat_str(err))
|
||||||
|
|
||||||
|
info['title'] = info['id']
|
||||||
|
|
||||||
|
links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage))
|
||||||
|
info['list'] = [
|
||||||
|
{
|
||||||
|
'type': 'reference',
|
||||||
|
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage),
|
||||||
|
}
|
||||||
|
for cpage in links]
|
||||||
|
|
||||||
|
results = []
|
||||||
|
for entry in info['list']:
|
||||||
|
assert entry['type'] == 'reference'
|
||||||
|
results += self.extract(entry['url'])
|
||||||
|
return results
|
||||||
Loading…
Reference in a new issue