Merge tag 'upstream/2015.11.27.1'

[youtubedl] / youtube_dl / extractor / safari.py

diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py
index 10251f29e033ef241618ed7985e214dc0e76cd51..91970426103c0384a4998407443907182d7976b5 100644 (file)
--- a/youtube_dl/extractor/safari.py
+++ b/youtube_dl/extractor/safari.py
@@ -4,14 +4,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from .brightcove import BrightcoveIE
+from .brightcove import BrightcoveLegacyIE

 
 

-from ..compat import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
+from ..compat import compat_urllib_parse

 from ..utils import (
     ExtractorError,
 from ..utils import (
     ExtractorError,

+    sanitized_Request,

     smuggle_url,
     std_headers,
 )
     smuggle_url,
     std_headers,
 )


@@ -20,7 +18,6 @@ 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>'
 class SafariBaseIE(InfoExtractor):
     _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
     _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'

-    _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com'

     _NETRC_MACHINE = 'safari'
 
     _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
     _NETRC_MACHINE = 'safari'
 
     _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'


@@ -37,9 +34,7 @@ class SafariBaseIE(InfoExtractor):
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:
     def _login(self):
         (username, password) = self._get_login_info()
         if username is None:

-            raise ExtractorError(
-                self._ACCOUNT_CREDENTIALS_HINT,
-                expected=True)
+            self.raise_login_required('safaribooksonline.com account is required')

 
         headers = std_headers
         if 'Referer' not in headers:
 
         headers = std_headers
         if 'Referer' not in headers:


@@ -61,7 +56,7 @@ class SafariBaseIE(InfoExtractor):
             'next': '',
         }
 
             'next': '',
         }
 

-        request = compat_urllib_request.Request(
+        request = sanitized_Request(

             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
         login_page = self._download_webpage(
             request, None, 'Logging in as %s' % username)
             self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
         login_page = self._download_webpage(
             request, None, 'Logging in as %s' % username)


@@ -83,7 +78,7 @@ class SafariIE(SafariBaseIE):
                                     library/view/[^/]+|
                                     api/v1/book
                                 )/
                                     library/view/[^/]+|
                                     api/v1/book
                                 )/

-                                (?P<course_id>\d+)/
+                                (?P<course_id>[^/]+)/

                                     (?:chapter(?:-content)?/)?
                                 (?P<part>part\d+)\.html
     '''
                                     (?:chapter(?:-content)?/)?
                                 (?P<part>part\d+)\.html
     '''


@@ -100,6 +95,10 @@ class SafariIE(SafariBaseIE):
     }, {
         'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
         'only_matching': True,
     }, {
         '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,

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):


@@ -111,18 +110,18 @@ class SafariIE(SafariBaseIE):
             '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
             part)
 
             '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
             part)
 

-        bc_url = BrightcoveIE._extract_brightcove_url(webpage)
+        bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)

         if not bc_url:
             raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
 
         if not bc_url:
             raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
 

-        return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove')
+        return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'BrightcoveLegacy')

 
 
 class SafariCourseIE(SafariBaseIE):
     IE_NAME = 'safari:course'
     IE_DESC = 'safaribooksonline.com online courses'
 
 
 
 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>\d+)/?(?:[#?]|$)'
+    _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'

 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
 
     _TESTS = [{
         'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',