mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 21:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

[safari] Improve and simplify

Browse source
This commit is contained in:
Sergey M․ 2015-03-26 23:57:46 +06:00
parent ac0df2350a
commit 31c4809827
1 changed files with 57 additions and 44 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

101
youtube_dl/extractor/safari.py
View file

@ -2,7 +2,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from .brightcove import BrightcoveIE from .brightcove import BrightcoveIE
@ -20,16 +19,18 @@
class SafariBaseIE(InfoExtractor): class SafariBaseIE(InfoExtractor):
_LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/' _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
_SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]+>Sign Out</a>' _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
_ACCOUNT_CREDENTIALS_HINT = ('Use --username and --password options to ' _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com'
'supply credentials for safaribooksonline.com ') _NETRC_MACHINE = 'safari'
_NETRC_MACHINE = 'safaribooksonline'
_API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
_API_FORMAT = 'json'
LOGGED_IN = False LOGGED_IN = False
def _real_initialize(self): def _real_initialize(self):
# We only need to log in once for courses or individual videos # We only need to log in once for courses or individual videos
if not SafariBaseIE.LOGGED_IN: if not self.LOGGED_IN:
self._login() self._login()
SafariBaseIE.LOGGED_IN = True SafariBaseIE.LOGGED_IN = True
@ -49,7 +50,7 @@ def _login(self):
'Downloading login form') 'Downloading login form')
csrf = self._html_search_regex( csrf = self._html_search_regex(
r"<input +type='hidden' +name='csrfmiddlewaretoken' +value='([^']+)' +/>", r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
login_page, 'csrf token') login_page, 'csrf token')
login_form = { login_form = {
@ -66,8 +67,9 @@ def _login(self):
request, None, 'Logging in as %s' % username) request, None, 'Logging in as %s' % username)
if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None: if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
raise ExtractorError('Login failed; make sure your credentials are correct and ' raise ExtractorError(
'try again.', expected=True) 'Login failed; make sure your credentials are correct and try again.',
expected=True)
self.to_screen('Login successful') self.to_screen('Login successful')
@ -75,69 +77,80 @@ def _login(self):
class SafariIE(SafariBaseIE): class SafariIE(SafariBaseIE):
IE_NAME = 'safari' IE_NAME = 'safari'
IE_DESC = 'safaribooksonline.com online video' IE_DESC = 'safaribooksonline.com online video'
_VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/' _VALID_URL = r'''(?x)https?://
'(?P<id>\d+)/(?P<part>part\d+)\.html') (?:www\.)?safaribooksonline\.com/
_TEST = { (?:
'url': ('https://www.safaribooksonline.com/library/view/' library/view/[^/]+|
'hadoop-fundamentals-livelessons/9780133392838/part00.html'), api/v1/book
)/
(?P<course_id>\d+)/
(?:chapter(?:-content)?/)?
(?P<part>part\d+)\.html
'''
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
'md5': '5b0c4cc1b3c1ba15dda7344085aa5592', 'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
'info_dict': { 'info_dict': {
'id': '9780133392838', 'id': '2842601850001',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Introduction', 'title': 'Introduction',
} },
} 'skip': 'Requires safaribooksonline account credentials',
}, {
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
course_id = mobj.group('course_id')
part = mobj.group('part') part = mobj.group('part')
webpage = self._download_webpage(url, part) webpage = self._download_webpage(
'%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
part)
bc_url = BrightcoveIE._extract_brightcove_url(webpage) bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if not bc_url: if not bc_url:
raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True) raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
return { return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove')
'_type': 'url',
'url': smuggle_url(bc_url, {'Referer': url}),
'ie_key': 'Brightcove'
}
class SafariCourseIE(SafariBaseIE): class SafariCourseIE(SafariBaseIE):
IE_NAME = 'safari:course' IE_NAME = 'safari:course'
IE_DESC = 'safaribooksonline.com online courses' IE_DESC = 'safaribooksonline.com online courses'
_VALID_URL = (r'https?://(?:www\.)?safaribooksonline\.com/library/view/' _VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>\d+)/?(?:[#?]|$)'
'(?P<course_path>[^/]+)/(?P<id>\d+)/?$')
_API_BASE = 'https://www.safaribooksonline.com/api/v1/book' _TESTS = [{
_API_FORMAT = 'json' '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): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) course_id = self._match_id(url)
course_path = mobj.group('course_path')
course_id = mobj.group('id')
webpage = self._download_webpage( course_json = self._download_json(
'%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),
course_path, 'Downloading course JSON') course_id, 'Downloading course JSON')
course_json = json.loads(webpage)
if 'chapters' not in course_json: if 'chapters' not in course_json:
raise ExtractorError('No chapters found for course %s' % course_id, expected=True) 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)]
entries = [ entries = [
self.url_result( self.url_result(chapter, 'Safari')
'https://www.safaribooksonline.com/library/view/%s/%s/part%s.html' % (course_path, for chapter in course_json['chapters']]
course_id,
part_id),
'Safari')
for part_id in parts]
course_title = course_json['title'] course_title = course_json['title']