Created
March 12, 2018 09:27
-
-
Save sayinserdar/7a19d2e93103835f1f772324df6b7841 to your computer and use it in GitHub Desktop.
Tiny python script for downloading pdf file through web site link
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
from bs4 import BeautifulSoup | |
import urllib.request | |
import requests | |
import os | |
with urllib.request.urlopen('Your URL') as response: | |
html_doc = response.read() | |
def download_file(url): | |
local_filename = url.split('/')[-1] | |
r = requests.get(url, stream=True) | |
with open(local_filename, 'wb') as f: | |
for chunk in r.iter_content(chunk_size=1024): | |
if chunk: | |
f.write(chunk) | |
return local_filename | |
base_url = 'Your URL' | |
soup = BeautifulSoup(html_doc, 'html.parser') | |
list = [] | |
for html in soup.find_all('a'): | |
length = len(html.get('href')) | |
if html.get('href')[length-3:length].lower() == "pdf": | |
list.append(base_url + html.get('href')) | |
for link in list: | |
print(link) | |
download_file(link) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment