Update upstream source from tag 'upstream/2017.12.31'

[youtubedl] / youtube_dl / extractor / safari.py

diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py
index 6ba91f202baadbfd72160cc739efde868a60d421..cc6698f882a5859883372b32dc71578ebe37da8a 100644 (file)
--- 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'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
     _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='([^']+)'",
@@ -60,22 +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'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>part\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
@@ -92,6 +91,9 @@ class SafariIE(SafariBaseIE):
         # 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):
@@ -100,13 +102,13 @@ class SafariIE(SafariBaseIE):
 
         webpage = self._download_webpage(url, video_id)
         reference_id = self._search_regex(
-            r'data-reference-id=(["\'])(?P<id>.+?)\1',
+            r'data-reference-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'kaltura reference id', group='id')
         partner_id = self._search_regex(
-            r'data-partner-id=(["\'])(?P<id>.+?)\1',
+            r'data-partner-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'kaltura widget id', group='id')
         ui_id = self._search_regex(
-            r'data-ui-id=(["\'])(?P<id>.+?)\1',
+            r'data-ui-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
             webpage, 'kaltura uiconf id', group='id')
 
         query = {
@@ -132,12 +134,15 @@ class SafariIE(SafariBaseIE):
 
 class SafariApiIE(SafariBaseIE):
     IE_NAME = 'safari:api'
-    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>part\d+)\.html'
+    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
 
-    _TEST = {
+    _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)
@@ -151,7 +156,14 @@ 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<id>[^/]+)/?(?:[#?]|$)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)|
+                            techbus\.safaribooksonline\.com
+                        )
+                        /(?P<id>[^/]+)/?(?:[#?]|$)
+                    '''
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
@@ -164,6 +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):