- _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 = 'safaribooksonline'
+ _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
+ _NETRC_MACHINE = 'safari'
+
+ _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
+ _API_FORMAT = 'json'
self._login()
SafariBaseIE.LOGGED_IN = True
def _login(self):
(username, password) = self._get_login_info()
if username is None:
self._login()
SafariBaseIE.LOGGED_IN = True
def _login(self):
(username, password) = self._get_login_info()
if username is None:
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
login_page = self._download_webpage(
request, None, 'Logging in as %s' % username)
if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
login_page = self._download_webpage(
request, None, 'Logging in as %s' % username)
if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
- _VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/'
- '(?P<id>\d+)/(?P<part>part\d+)\.html')
- _TEST = {
- 'url': ('https://www.safaribooksonline.com/library/view/'
- 'hadoop-fundamentals-livelessons/9780133392838/part00.html'),
+ _VALID_URL = r'''(?x)https?://
+ (?:www\.)?safaribooksonline\.com/
+ (?:
+ library/view/[^/]+|
+ api/v1/book
+ )/
+ (?P<course_id>[^/]+)/
+ (?:chapter(?:-content)?/)?
+ (?P<part>part\d+)\.html
+ '''
+
+ _TESTS = [{
+ 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
+ },
+ 'skip': 'Requires safaribooksonline account credentials',
+ }, {
+ '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):
mobj = re.match(self._VALID_URL, url)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- webpage = self._download_webpage(url, part)
- bc_url = BrightcoveIE._extract_brightcove_url(webpage)
+ webpage = self._download_webpage(
+ '%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
+ part)
+
+ bc_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
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'
- _API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
- _API_FORMAT = 'json'
+ _TESTS = [{
+ 'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
+ 'info_dict': {
+ 'id': '9780133392838',
+ 'title': 'Hadoop Fundamentals LiveLessons',
+ },
+ 'playlist_count': 22,
+ 'skip': 'Requires safaribooksonline account credentials',
+ }, {
+ 'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
+ 'only_matching': True,
+ }]
- mobj = re.match(self._VALID_URL, url)
- course_path = mobj.group('course_path')
- course_id = mobj.group('id')
+ course_id = self._match_id(url)
'%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
'%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
- raise ExtractorError('No chapters found for course %s' % course_id, expected=True)
-
- num_parts = len(course_json['chapters'])
- parts = ['%02d' % part for part in range(num_parts)]
+ raise ExtractorError(
+ 'No chapters found for course %s' % course_id, expected=True)