Created
January 4, 2016 14:43
-
-
Save lantip/b2fa24b111e59d41806b to your computer and use it in GitHub Desktop.
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 | |
# -*- coding:utf-8 -*- | |
import requests | |
import json | |
from bs4 import BeautifulSoup | |
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 | |
# mari kita koding | |
main_url = 'https://en.wikipedia.org/wiki/User_talk:Crisco_1492/Library' | |
# download the page | |
r = requests.get(main_url) | |
soup = BeautifulSoup(r.text,'html.parser') | |
listfile = [] | |
# lets start parsing | |
# first we'll collect all the div with class 'thumb' | |
thumbs = soup.find_all('div',attrs={'class':'thumb'}) | |
#iterate the thumbs | |
for t in thumbs: | |
# find the link inside the div | |
link = t.find_all('a') | |
# find the image. fck, haruse ndak perlu yang di atas, tapi yo ben lah | |
thu = link[0].find_all('img') | |
# get attribute srcset | |
set = thu[0]['srcset'] | |
# get the file link | |
file = set.split('.pdf/')[0].replace('thumb/','')+'.pdf' | |
listfile.append(file) | |
for l in listfile: | |
namfile = l.split('/')[-1] | |
print 'downloading '+ namfile | |
download_file('http:'+l) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
untuk pemakaian:
simpan script ini sebagai wiki_downloader.py
install requests
install beautifulsoup4
jalankan: python wiki_downloader.py