X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fsafari.py;h=08ddbe3c4222879cade93fd9a5433e1d9c4e6e49;hb=b1c6f21c741b7f18b2b46165be0a3539735a6184;hp=ae619636ce643d78bcd53e4cd31ec7e549a1652b;hpb=bcb668de189b92bd1dcad661d50ae981f25deca4;p=youtube-dl.git
diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py
index ae619636c..08ddbe3c4 100644
--- a/youtube_dl/extractor/safari.py
+++ b/youtube_dl/extractor/safari.py
@@ -4,12 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from .brightcove import BrightcoveLegacyIE
from ..utils import (
ExtractorError,
sanitized_Request,
- smuggle_url,
std_headers,
urlencode_postdata,
update_url_query,
@@ -21,22 +19,22 @@ class SafariBaseIE(InfoExtractor):
_SUCCESSFUL_LOGIN_REGEX = r']*>Sign Out'
_NETRC_MACHINE = 'safari'
- _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
+ _API_BASE = 'https://www.safaribooksonline.com/api/v1'
_API_FORMAT = 'json'
LOGGED_IN = False
def _real_initialize(self):
- return
- # We only need to log in once for courses or individual videos
- if not self.LOGGED_IN:
- self._login()
- SafariBaseIE.LOGGED_IN = True
+ self._login()
def _login(self):
+ # We only need to log in once for courses or individual videos
+ if self.LOGGED_IN:
+ return
+
(username, password) = self._get_login_info()
if username is None:
- self.raise_login_required('safaribooksonline.com account is required')
+ return
headers = std_headers.copy()
if 'Referer' not in headers:
@@ -69,22 +67,15 @@ class SafariBaseIE(InfoExtractor):
'Login failed; make sure your credentials are correct and try again.',
expected=True)
+ SafariBaseIE.LOGGED_IN = True
+
self.to_screen('Login successful')
class SafariIE(SafariBaseIE):
IE_NAME = 'safari'
IE_DESC = 'safaribooksonline.com online video'
- _VALID_URL = r'''(?x)https?://
- (?:www\.)?safaribooksonline\.com/
- (?:
- library/view/[^/]+|
- api/v1/book
- )/
- (?P[^/]+)/
- (?:chapter(?:-content)?/)?
- (?Ppart\d+)\.html
- '''
+ _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P[^/]+)/(?P[^/?#&]+)\.html'
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
@@ -97,30 +88,69 @@ class SafariIE(SafariBaseIE):
'upload_date': '20150724',
'uploader_id': 'stork',
},
- }, {
- 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
- 'only_matching': True,
}, {
# non-digits in course id
'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
'only_matching': True,
+ }, {
+ 'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
+ 'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- course_id = mobj.group('course_id')
- part = mobj.group('part')
-
- webpage = self._download_webpage(url, '%s/%s' % (course_id, part))
- reference_id = self._search_regex(r'data-reference-id="([^"]+)"', webpage, 'kaltura reference id')
- partner_id = self._search_regex(r'data-partner-id="([^"]+)"', webpage, 'kaltura widget id')
- ui_id = self._search_regex(r'data-ui-id="([^"]+)"', webpage, 'kaltura uiconf id')
-
- return self.url_result(update_url_query('https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', {
+ video_id = '%s/%s' % (mobj.group('course_id'), mobj.group('part'))
+
+ webpage = self._download_webpage(url, video_id)
+ reference_id = self._search_regex(
+ r'data-reference-id=(["\'])(?P.+?)\1',
+ webpage, 'kaltura reference id', group='id')
+ partner_id = self._search_regex(
+ r'data-partner-id=(["\'])(?P.+?)\1',
+ webpage, 'kaltura widget id', group='id')
+ ui_id = self._search_regex(
+ r'data-ui-id=(["\'])(?P.+?)\1',
+ webpage, 'kaltura uiconf id', group='id')
+
+ query = {
'wid': '_%s' % partner_id,
'uiconf_id': ui_id,
'flashvars[referenceId]': reference_id,
- }), 'Kaltura')
+ }
+
+ if self.LOGGED_IN:
+ kaltura_session = self._download_json(
+ '%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
+ video_id, 'Downloading kaltura session JSON',
+ 'Unable to download kaltura session JSON', fatal=False)
+ if kaltura_session:
+ session = kaltura_session.get('session')
+ if session:
+ query['flashvars[ks]'] = session
+
+ return self.url_result(update_url_query(
+ 'https://cdnapisec.kaltura.com/html5/html5lib/v2.37.1/mwEmbedFrame.php', query),
+ 'Kaltura')
+
+
+class SafariApiIE(SafariBaseIE):
+ IE_NAME = 'safari:api'
+ _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P[^/]+)/chapter(?:-content)?/(?P[^/?#&]+)\.html'
+
+ _TESTS = [{
+ 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ part = self._download_json(
+ url, '%s/%s' % (mobj.group('course_id'), mobj.group('part')),
+ 'Downloading part JSON')
+ return self.url_result(part['web_url'], SafariIE.ie_key())
class SafariCourseIE(SafariBaseIE):
@@ -146,7 +176,7 @@ class SafariCourseIE(SafariBaseIE):
course_id = self._match_id(url)
course_json = self._download_json(
- '%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
+ '%s/book/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
course_id, 'Downloading course JSON')
if 'chapters' not in course_json:
@@ -154,7 +184,7 @@ class SafariCourseIE(SafariBaseIE):
'No chapters found for course %s' % course_id, expected=True)
entries = [
- self.url_result(chapter, 'Safari')
+ self.url_result(chapter, SafariApiIE.ie_key())
for chapter in course_json['chapters']]
course_title = course_json['title']