Not much

Author: hemangsk

Templates.txt

@@ -0,0 +1,34 @@
+from BeautifulSoup import BeautifulSoup
+import urllib2
+import urllib
+import sys
+Soup=BeautifulSoup
+links=[]
+url="http://www.geeksforgeeks.org/data-structures/"
+f=urllib2.urlopen(url)
+page=f.read()
+f.close()
+page=unicode(page,'utf-8')
+soup=Soup(page)
+j=0
+for a in soup.findAll('a', href=True):
+    if "http://geeksquiz.com/linked-list-set-1-introduction/" in a['href']:
+        j=1
+    if j==1:
+        links.append(a['href'])
+i=0
+for x in links:
+    if "#" in x:
+        links.pop(i)
+    i=i+1
+print links
+final=open("final.txt","w")
+for x in links:
+    print x
+    f=urllib.urlopen(x)
+    page=f.read()
+    f.close()
+    page=unicode(page,'utf-8')
+    page=page[page.find("<header class="):page.find("<script async src=")]
+    soup=Soup(page)
+    final.write(soup.getText().encode('utf-8'))

scraping-py/final.txt

@@ -0,0 +1,15 @@
+#include <iostream>
+using namespace std;
+int main(int argc, char const *argv[]) {
+  int a;
+  int b;
+  cout<<"Enter a";
+  cin>>a;
+  cout<<"Enter b";
+  cin>>b;
+  cout<<"Sum=A+b"<<a+b;
+  cout<<endl;
+  cout<<"This";
+  cout<<endl;
+  return 0;
+}

scraping-py/geeksforgeeks.py

@@ -0,0 +1,14 @@
+import wget
+import urllib2
+from BeautifulSoup import BeautifulSoup
+Soup=BeautifulSoup
+import BeautifulSoup
+i=0
+url="http://stim.ee.uh.edu/education/ece-3340-numerical-methods/"
+f=urllib2.urlopen(url)
+page=f.read()
+f.close()
+soup=Soup(page)
+for link in soup.findAll('a', href=True):
+    if "bitbucket" in link['href'] and "ppt" not in link['href']:
+        filename=wget.download(link['href'])

scraping-py/p.out

@@ -0,0 +1,21 @@
+from BeautifulSoup import BeautifulSoup
+import urllib2
+import wget
+import requests
+Soup=BeautifulSoup
+import BeautifulSoup
+
+str1="Covering the nitty-gritties of C++ templates"
+str2="This article, along with any associated source code and files, is licensed under"
+url="http://www.codeproject.com/Articles/257589/An-Idiots-Guide-to-Cplusplus-Templates-Part";
+f=urllib2.urlopen(url)
+page=f.read()
+f.close()
+
+page=page[page.find(str1):page.find(str2)]
+
+soup=Soup(page)
+text = soup.getText()
+f=open("Templates.txt", "w")
+f.write(text.encode("utf-8"))
+f.close()

scraping-py/test.cpp

@@ -0,0 +1,13 @@
+import wget
+import urllib2
+from BeautifulSoup import BeautifulSoup
+Soup=BeautifulSoup
+import BeautifulSoup
+i=0
+url="http://stim.ee.uh.edu/education/ece-3340-numerical-methods/"
+f=urllib2.urlopen(url)
+page=f.read()
+f.close()
+soup=Soup(page)
+for link in soup.findAll('a', href=True):
+    print link['href']

scraping-py/testingscript.py

@@ -4,7 +4,7 @@
 import requests
 Soup=BeautifulSoup
 import BeautifulSoup
-url="http://xampaperz.com/xampaperz/xampaperz/MAIT/xampaperz/subject.php?id=1&semkey=%3Cspan%20class="x x-first x-last">8&sem=8thsemcse&semester=8th&main=xampaerl_cse&stream_get=Computer"+ "%20"+"Science"
+url="http://xampaperz.com/xampaperz/xampaperz/MAIT/xampaperz/subject.php?id=1&semkey=%3Cspan%20class="x x-first x-last">7&sem=7thsemcse&semester=7th&main=xampaerl_cse&stream_get=Computer"+ "%20"+"Science"
 f=urllib2.urlopen(url)
 page=f.read()
 f.close()
@@ -35,15 +35,17 @@
             paper.append("http:xampaperz/xampaperz/MAIT/xampaperz/" + a['href'])
 final=[]
 for a in paper:
-    a= a[a.find("&paper_url")+len("&paper_url")+1:a.find(".jpg")] +".jpg"
+    a= a[a.find("&paper_url")+len("&paper_url")+1:a.find(".jpg")] +"2.jpg"
+    b= a[a.find("&paper_url")+len("&paper_url")+1:a.find(".jpg")] +".jpg"
     print a
     final.append(a)
+    final.append(b)
 
 i=0
 for x in final:
     response = requests.get(x)
     if response.status_code == 200:
-        f = open("8th Sem final" + str(i)+ ".jpg", 'wb')
+        f = open("7th Sem  Part 2 final" + str(i)+ ".jpg", 'wb')
         f.write(response.content)
         f.close()
     i=i+1