├── README.md
├── LICENSE
└── geeksforgeeks-pdf.py


/README.md:
--------------------------------------------------------------------------------
1 | geeksforgeeks-pdf
2 | =================
3 | 
4 | This Python script aimed to download all Amazon Interview Experience from GeeksforGeeks website. You can modify this script to download as per your need.
5 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | The MIT License (MIT)
 2 | 
 3 | Copyright (c) 2014 Arun Prakash
 4 | 
 5 | Permission is hereby granted, free of charge, to any person obtaining a copy
 6 | of this software and associated documentation files (the "Software"), to deal
 7 | in the Software without restriction, including without limitation the rights
 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 | 
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 | 
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 | 
23 | 


--------------------------------------------------------------------------------
/geeksforgeeks-pdf.py:
--------------------------------------------------------------------------------
 1 | import httplib2
 2 | import pdfcrowd
 3 | from bs4 import BeautifulSoup, SoupStrainer
 4 | 
 5 | http = httplib2.Http()
 6 | s= 'http://www.geeksforgeeks.org/'
 7 | i=0
 8 | to_crawl=[]
 9 | to_crawl.append(s)
10 | status, response = http.request(s)
11 | crawled=[]
12 | crawled.append(s)
13 | 
14 | 
15 | for link in BeautifulSoup(response, parse_only=SoupStrainer('a')):
16 |         if link.has_attr('href'):
17 |             li=link['href']
18 |             #print li
19 |             if li.find('http://www.geeksforgeeks.org')==0 and li not in crawled and li.find('forums')<0:
20 |                 to_crawl.append(li)
21 |             
22 | 
23 | #print to_crawl
24 | print len(to_crawl)
25 | count=0
26 | 
27 | def get_page(page):
28 |     import urllib2
29 |     source=urllib2.urlopen(page)
30 |     return source.read()
31 | 
32 | 
33 | def save_as_pdf(s):
34 |     global i
35 |     try:
36 |         client = pdfcrowd.Client("mkap1234", "fc5ada9fbd1c55f46822d6e9e985a9bb")
37 |         output_file = open('amazon'+str(i)+'.pdf', 'wb')
38 |         i=i+1
39 |         html=get_page(s)
40 |         client.convertHtml(html, output_file)
41 |         output_file.close()
42 |     except pdfcrowd.Error,why:
43 |         print 'Failed:', why
44 | 
45 | 
46 | while len(to_crawl):
47 |     b=to_crawl.pop()
48 |     if b.find('http://www.geeksforgeeks.org')==0 and b not in crawled and b.find('forums')<0:
49 |         count=count+1
50 |         print count
51 |         crawled.append(b)
52 |         status, response = http.request(b)
53 |         for link in BeautifulSoup(response, parse_only=SoupStrainer('a')):
54 |             if link.has_attr('href'):
55 |                 li=link['href']
56 |                 if b.find('http://www.geeksforgeeks.org')==0 and li not in crawled:
57 |                     to_crawl.append(li)
58 |                     
59 |                 
60 | 
61 | 
62 | 
63 | amazon=[]
64 | 
65 | for st in crawled:
66 |     if st.find('amazon')>=0 and st.find('#')<0 and st.find('tag')<0 and st.find('forum')<0:
67 |         print st
68 |         amazon.append(st)
69 | 
70 | 
71 | 
72 | print "Finished"
73 | print len(amazon)
74 |         
75 |   
76 | for page in amazon:
77 |     save_as_pdf(page)
78 | 


--------------------------------------------------------------------------------