1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 04:28:02 +01:00
youtube-dl/youtube_dl/extractor/safari.py

159 lines
5.2 KiB
Python
Raw Normal View History

# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .brightcove import BrightcoveIE
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
smuggle_url,
std_headers,
)
class SafariBaseIE(InfoExtractor):
_LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
2015-03-26 18:57:46 +01:00
_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'
LOGGED_IN = False
def _real_initialize(self):
# We only need to log in once for courses or individual videos
2015-03-26 18:57:46 +01:00
if not self.LOGGED_IN:
self._login()
SafariBaseIE.LOGGED_IN = True
def _login(self):
(username, password) = self._get_login_info()
if username is None:
2015-08-26 17:26:24 +02:00
self.raise_login_required('safaribooksonline.com account is required')
headers = std_headers
if 'Referer' not in headers:
headers['Referer'] = self._LOGIN_URL
login_page = self._download_webpage(
self._LOGIN_URL, None,
'Downloading login form')
csrf = self._html_search_regex(
2015-03-26 18:57:46 +01:00
r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
login_page, 'csrf token')
login_form = {
'csrfmiddlewaretoken': csrf,
'email': username,
'password1': password,
'login': 'Sign In',
'next': '',
}
request = compat_urllib_request.Request(
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:
2015-03-26 18:57:46 +01:00
raise ExtractorError(
'Login failed; make sure your credentials are correct and try again.',
expected=True)
self.to_screen('Login successful')
class SafariIE(SafariBaseIE):
IE_NAME = 'safari'
IE_DESC = 'safaribooksonline.com online video'
2015-03-26 18:57:46 +01:00
_VALID_URL = r'''(?x)https?://
(?:www\.)?safaribooksonline\.com/
(?:
library/view/[^/]+|
api/v1/book
)/
2015-06-15 01:27:43 +02:00
(?P<course_id>[^/]+)/
2015-03-26 18:57:46 +01:00
(?:chapter(?:-content)?/)?
(?P<part>part\d+)\.html
'''
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
'info_dict': {
2015-03-26 18:57:46 +01:00
'id': '2842601850001',
'ext': 'mp4',
'title': 'Introduction',
2015-03-26 18:57:46 +01:00
},
'skip': 'Requires safaribooksonline account credentials',
}, {
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
'only_matching': True,
2015-06-15 17:36:30 +02:00
}, {
# non-digits in course id
'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
'only_matching': True,
2015-03-26 18:57:46 +01:00
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2015-03-26 18:57:46 +01:00
course_id = mobj.group('course_id')
part = mobj.group('part')
2015-03-26 18:57:46 +01:00
webpage = self._download_webpage(
'%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
part)
bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if not bc_url:
raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
2015-03-26 18:57:46 +01:00
return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove')
class SafariCourseIE(SafariBaseIE):
IE_NAME = 'safari:course'
IE_DESC = 'safaribooksonline.com online courses'
2015-06-15 01:27:43 +02:00
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>[^/]+)/?(?:[#?]|$)'
2015-03-26 18:57:46 +01:00
_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,
}]
def _real_extract(self, url):
2015-03-26 18:57:46 +01:00
course_id = self._match_id(url)
2015-03-26 18:57:46 +01:00
course_json = self._download_json(
'%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
2015-03-26 18:57:46 +01:00
course_id, 'Downloading course JSON')
if 'chapters' not in course_json:
2015-03-26 18:57:46 +01:00
raise ExtractorError(
'No chapters found for course %s' % course_id, expected=True)
entries = [
2015-03-26 18:57:46 +01:00
self.url_result(chapter, 'Safari')
for chapter in course_json['chapters']]
course_title = course_json['title']
return self.playlist_result(entries, course_id, course_title)