fork download
copy 
  1. # A resumable Safari Books Online Video downloader
  2. # Main reference: https://m...content-available-to-author-only...b.io/tools/2017/02/02/safari-downloader.html
  3.  
  4. from bs4 import BeautifulSoup
  5. import requests
  6. import os
  7. import re
  8. import subprocess
  9. import unicodedata
  10. import string
  11.  
  12. import config
  13. # Create a config.py file with the following content:
  14. # class Config:
  15. #     URL = 'https://w...content-available-to-author-only...e.com/library/view/strata-data-conference/9781491985373/'
  16. #     DOMAIN = 'https://w...content-available-to-author-only...e.com'
  17. #     OUTPUT_FOLDER = 'D:\\Strata Data Conference 2017 Singapore'
  18. #     USERNAME = 'your_email_address'
  19. #     PASSWORD = 'your_password'
  20. #     DOWNLOADER = './youtube-dl.exe' # Please download from https://g...content-available-to-author-only...b.com/rg3/youtube-dl
  21.  
  22. class SafariDownloader:
  23.  
  24. 	def slugify(self, value):
  25. 		"""
  26. 		Normalizes string, converts to lowercase, removes non-alpha characters,
  27. 		and converts spaces to hyphens.
  28. 		"""
  29.  
  30. 		value = re.sub('[^\w\s-]', '', value).strip().lower()
  31. 		value = re.sub('[-\s]+', '-', value)
  32. 		return value
  33.  
  34. 	def __init__(self, url, output_folder, username, password, domain='https://w...content-available-to-author-only...e.com', downloader_path='./youtube-dl.exe'):
  35. 		self.output_folder = output_folder
  36. 		self.username = username
  37. 		self.password = password
  38. 		self.domain = domain
  39. 		self.downloader_path = downloader_path
  40.  
  41. 		req = requests.get(url)
  42. 		soup = BeautifulSoup(req.text, 'html.parser')
  43. 		self.topics = soup.find_all('li', class_='toc-level-1') # top-level topic titles
  44. 		# Update youtube-dl first
  45. 		subprocess.run([self.downloader_path, "-U"])
  46.  
  47. 	def validify(self, filename):
  48. 		valid_chars = "-_.() %s%s" % (string.ascii_letters, string.digits)
  49. 		valid_chars = frozenset(valid_chars)
  50. 		# The unicodedata.normalize call replaces accented characters with the unaccented equivalent,
  51. 		# which is better than simply stripping them out. After that all disallowed characters are removed.
  52. 		cleaned_filename = unicodedata.normalize('NFKD', filename).encode('ascii', 'ignore').decode('ascii')
  53. 		return ''.join(c for c in cleaned_filename if c in valid_chars)
  54.  
  55. 	def download(self):
  56. 		i = 0
  57. 		for topic in self.topics:
  58. 			i = i + 1
  59. 			topic_name = '{:03d} - {}'.format(i, self.slugify(topic.a.text))
  60. 			# Creating folder to put the videos in
  61. 			save_folder = '{}/{}'.format(self.output_folder, topic_name)
  62. 			os.makedirs(save_folder, exist_ok=True)
  63. 			# You can choose to skip these topic_name, comment these three lines if you do not want to skip any
  64. 			if topic_name in ('Keynotes', 'Strata Business Summit', 'Sponsored'):
  65. 				print("Skipping {}...".format(topic_name))
  66. 				continue
  67. 			for index, video in enumerate(topic.ol.find_all('a')):
  68. 				video_name = '{:03d} - {}'.format(index + 1, video.text)
  69. 				video_name = self.slugify(video_name)
  70. 				video_name = self.validify(video_name)
  71. 				video_url = video.get('href')
  72. 				video_out = '{}/{}.mp4'.format(save_folder, video_name)
  73. 				# Check if file already exists
  74. 				if os.path.isfile(video_out):
  75. 					print("File {} already exists! Skipping...".format(video_out))
  76. 					continue
  77. 				print("Downloading {} ...".format(video_name))
  78. 				print("Link {} ...".format(video_url))
  79. 				subprocess.run([self.downloader_path, "-u", self.username, "-p", self.password, "--verbose", "--output", video_out, video_url])
  80.  
  81. if __name__ == '__main__':
  82. 	app_config = config.Config
  83. 	downloader = SafariDownloader(url=app_config.URL, output_folder=app_config.OUTPUT_FOLDER,
  84.                                   username=app_config.USERNAME, password=app_config.PASSWORD,
  85.                                   domain=app_config.DOMAIN, downloader_path=app_config.DOWNLOADER)
  86. 	downloader.download()
Runtime error #stdin #stdout #stderr 0.16s 26808KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Standard output is empty
stderr
copy 
Traceback (most recent call last):
  File "./prog.py", line 5, in <module>
ImportError: No module named 'requests'
https://ideone.com/ib8n7W
language:
Python 3 (python  3.9.5)
created:
6 years ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!