Web-Scraping-and-Python-Codes/Tutorialspoint_PDF_download.py at master · jatinsinghal1921/Web-Scraping-and-Python-Codes · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
from bs4 import BeautifulSoup
import requests
import urllib
import urllib2


def get_PDF():
    url = raw_input("Provide the link of the page : ")
    page_file = urllib2.urlopen(url)
    page_html = page_file.read()
    page_file.close()

    soup1 = BeautifulSoup(page_html, "html.parser")


    for button1 in soup1.find_all("button", attrs={"class":"btn btn-default btn-sm btn-buy-tutorial"}):
        for a1 in button1.find_all("a"):
            pdf_page_link = "http://www.tutorialspoint.com" + str(a1['href'])

    print pdf_page_link

    pdf_file = urllib2.urlopen(pdf_page_link)
    pdf_html = pdf_file.read()
    pdf_file.close()

    soup2 = BeautifulSoup(pdf_html, "html.parser")

    for div in soup2.find_all("div", attrs={'class' : "pdf-btn"}):
        for a2 in div.find_all("a"):
            pdf_title = str(a2["title"]) + str(".pdf")

    for a3 in soup2.find_all("a", attrs={"class" : "left"}):
        pdf_link = "http://www.tutorialspoint.com" + str(a3['href'])


    print pdf_link
    urllib.urlretrieve(pdf_link, pdf_title)

    #urllib.urlretrieve(pdf_link, final_title)

get_PDF()