Created
November 20, 2012 21:26
-
-
Save mrabbitt/4121269 to your computer and use it in GitHub Desktop.
Script to download all PDF files for a particular version of Splunk documentation.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
''' | |
Script to download all PDF files for a particular version of Splunk documentation. | |
Requirements: | |
requests: http://docs.python-requests.org | |
beautifulsoup4: http://www.crummy.com/software/BeautifulSoup/ | |
(pip install -U requests beautifulsoup4) | |
Author: Michael Rabbitt (https://github.com/mrabbitt) | |
''' | |
from __future__ import unicode_literals, print_function | |
import os.path | |
import shutil | |
import re | |
import sys | |
import tempfile | |
import requests | |
from bs4 import BeautifulSoup | |
manual_link_regex = re.compile(r'^/Documentation/Splunk/([\d.]+)/([^/]+)/(.+)$') | |
filename_regex = re.compile(r'filename="([^"]+)"') | |
def getDownloadFileName(response, default_name): | |
'''Determines file name from a response object based on its headers | |
Rerverts to `default_name` if no name is suggested by the response headers.''' | |
if response.headers.has_key('content-disposition'): | |
match = filename_regex.match(response.headers['content-disposition']) | |
if match: | |
return match.group(1) | |
return default_name | |
def main(download_directory, target_version): | |
response = requests.get('http://docs.splunk.com/Documentation/Splunk/{0}'.format(target_version)) | |
page = BeautifulSoup(response.text) | |
manual_links = [div.find('a') for div in page.find_all('div', class_='manualmodule')] | |
for manual_link in manual_links: | |
match = manual_link_regex.match(manual_link.attrs['href']) | |
doc_description = manual_link.text.strip() | |
(version, section, docname) = match.groups() | |
pdf_url = 'http://docs.splunk.com/index.php?title=Documentation:Splunk:{0}:{1}:{2}&action=pdfbook'.format(section, docname, version) | |
print('Downloading "{0}" from <{1}>...'.format(doc_description, pdf_url)) | |
pdf_response = requests.get(pdf_url) | |
file_name = getDownloadFileName(pdf_response, 'Splunk-{0}-{1}.pdf'.format(version, section)) | |
with tempfile.NamedTemporaryFile(suffix=file_name, delete=False) as temp_file: | |
temp_file.write(pdf_response.content) | |
target_path = os.path.join(download_directory, file_name) | |
print('Moving temporary file to {0}'.format(target_path)) | |
shutil.move(temp_file.name, target_path) | |
print('Complete') | |
if __name__ == '__main__': | |
if len(sys.argv) == 3: | |
download_directory = sys.argv[1] | |
target_version = sys.argv[2] if len(sys.argv) == 3 else 'latest' | |
if os.path.isdir(download_directory): | |
main(download_directory, target_version) | |
else: | |
print('No such directory: {0}'.format(download_directory), file=sys.stderr) | |
else: | |
print('''Usage: {0} PATH_TO_DOWNLOAD_DIR VERSION'''.format(os.path.basename(__file__)), file=sys.stderr) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment