Skip to content

Updated to Changes & added file name support #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Thuruv wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Updated to Changes & added file name support #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 12 additions & 20 deletions GFG_article_extractor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,44 +1,36 @@
#--------------------------------------------------
#--------------------------------------------------
# Name: GeeksForGeeks Article Extractor
# Purpose: To download and save articles filed under each and every tag mentioned in www.geeksforgeeks.org
#
#--------------------------------------------------
#--------------------------------------------------


#!/usr/bin/python
# -*- coding: utf-8 -*-

from bs4 import BeautifulSoup
import urllib2
import os


AllTags = ['interview-experience','advance-data-structures','dynamic-programming','Greedy-Algorithm','backtracking','pattern-searching','divide-and-conquer','graph','MathematicalAlgo','recursion','Java']

path = "E:\GeeksForGeeks\\" # Specify your path here

AllTags = ['Greedy-Algorithm']

path = ''

def ExtractMainLinks(AllTags,path):
for i in AllTags:
newpath = path + i
os.mkdir(newpath)
url = "http://www.geeksforgeeks.org/tag/" + i +"/"
data = urllib2.urlopen(url).read()
soup = BeautifulSoup(data)
allLinks = soup.findAll("h2",class_="post-title")
soup = BeautifulSoup(data,"html.parser")
allLinks = soup.findAll("h2",class_="entry-title")
listofLinks = []
for link in allLinks:
mainLink = str(link.findAll("a")[0]).split("<a href=")[1].split('rel="bookmark"')[0].strip('"').split('"')[0]
listofLinks.append(mainLink)
Extract_And_Save_Page_Data(listofLinks,newpath,i)
listofLinks.append([mainLink,mainLink.split('/')[3]])
Extract_And_Save_Page_Data(listofLinks)



def Extract_And_Save_Page_Data(listofLinks,newpath,i):
def Extract_And_Save_Page_Data(listofLinks):
No = 0
for item in listofLinks:
pageData = urllib2.urlopen(item).read()
filePath = newpath +"\\" +str(i)+" "+str(No+1)+".html"
pageData = urllib2.urlopen(item[0]).read()
filePath = item[1]+".html"
No = No +1
with open(filePath,"wb") as f:
f.write(str(pageData))
Expand Down