X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsafari.py;h=cc6698f882a5859883372b32dc71578ebe37da8a;hb=70d35d166c1cfb14af20fb6d45ed820b6249f941;hp=256396bb8c21174fdaca4524c0b21d1ef7f802a9;hpb=83548824c29ccdf53a4659260aa3898939833882;p=youtube-dl
diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py
index 256396bb8..cc6698f88 100644
--- a/youtube_dl/extractor/safari.py
+++ b/youtube_dl/extractor/safari.py
@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
from __future__ import unicode_literals
import re
@@ -16,7 +16,6 @@ from ..utils import (
class SafariBaseIE(InfoExtractor):
_LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
- _SUCCESSFUL_LOGIN_REGEX = r']*>Sign Out'
_NETRC_MACHINE = 'safari'
_API_BASE = 'https://www.safaribooksonline.com/api/v1'
@@ -28,10 +27,6 @@ class SafariBaseIE(InfoExtractor):
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:
return
@@ -39,11 +34,17 @@ class SafariBaseIE(InfoExtractor):
headers = std_headers.copy()
if 'Referer' not in headers:
headers['Referer'] = self._LOGIN_URL
- login_page_request = sanitized_Request(self._LOGIN_URL, headers=headers)
login_page = self._download_webpage(
- login_page_request, None,
- 'Downloading login form')
+ self._LOGIN_URL, None, 'Downloading login form', headers=headers)
+
+ def is_logged(webpage):
+ return any(re.search(p, webpage) for p in (
+ r'href=["\']/accounts/logout/', r'>Sign Out<'))
+
+ if is_logged(login_page):
+ self.LOGGED_IN = True
+ return
csrf = self._html_search_regex(
r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
@@ -60,31 +61,20 @@ class SafariBaseIE(InfoExtractor):
request = sanitized_Request(
self._LOGIN_URL, urlencode_postdata(login_form), headers=headers)
login_page = self._download_webpage(
- request, None, 'Logging in as %s' % username)
+ request, None, 'Logging in')
- if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
+ if not is_logged(login_page):
raise ExtractorError(
'Login failed; make sure your credentials are correct and try again.',
expected=True)
- SafariBaseIE.LOGGED_IN = True
-
- self.to_screen('Login successful')
+ self.LOGGED_IN = True
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',
@@ -97,24 +87,29 @@ 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')
+ 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).)+)\1',
+ webpage, 'kaltura reference id', group='id')
+ partner_id = self._search_regex(
+ r'data-partner-id=(["\'])(?P(?:(?!\1).)+)\1',
+ webpage, 'kaltura widget id', group='id')
+ ui_id = self._search_regex(
+ r'data-ui-id=(["\'])(?P(?:(?!\1).)+)\1',
+ webpage, 'kaltura uiconf id', group='id')
query = {
'wid': '_%s' % partner_id,
@@ -125,7 +120,7 @@ class SafariIE(SafariBaseIE):
if self.LOGGED_IN:
kaltura_session = self._download_json(
'%s/player/kaltura_session/?reference_id=%s' % (self._API_BASE, reference_id),
- course_id, 'Downloading kaltura session JSON',
+ video_id, 'Downloading kaltura session JSON',
'Unable to download kaltura session JSON', fatal=False)
if kaltura_session:
session = kaltura_session.get('session')
@@ -137,11 +132,38 @@ class SafariIE(SafariBaseIE):
'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):
IE_NAME = 'safari:course'
IE_DESC = 'safaribooksonline.com online courses'
- _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P[^/]+)/?(?:[#?]|$)'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)|
+ techbus\.safaribooksonline\.com
+ )
+ /(?P[^/]+)/?(?:[#?]|$)
+ '''
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
@@ -154,6 +176,9 @@ class SafariCourseIE(SafariBaseIE):
}, {
'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
'only_matching': True,
+ }, {
+ 'url': 'http://techbus.safaribooksonline.com/9780134426365',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -168,7 +193,7 @@ 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']