Created
February 8, 2016 13:47
-
-
Save utkarshmalik211/f1aabe4bbe38d81275fd to your computer and use it in GitHub Desktop.
Python script to scrape a given amazon page and list all the prices with item names (Basicaly for books)
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
from bs4 import BeautifulSoup | |
from urllib.request import urlopen | |
import re | |
try: | |
html=urlopen("http://www.amazon.in/b/ref=BizStrategy?_encoding=UTF8&node=1318070031&pf_rd_m=A1VBAL9TL5WCBF&pf_rd_s=merchandised-search-4&pf_rd_r=175CVN4B0C6BS94WK9BH&pf_rd_t=101&pf_rd_p=799588247&pf_rd_i=976389031").read() | |
except: | |
print("Connection Error") | |
else: | |
bsobj=BeautifulSoup(html,"html.parser") | |
for tag in bsobj.findAll('h2',{"class":"a-size-medium a-color-null s-inline s-access-title a-text-normal"}): | |
print(tag.get_text()) | |
try: | |
a=tag.find_next('a',{"title":"Kindle Edition"}).find_next('span',{"class":"a-size-base a-color-price s-price a-text-bold"}).get_text() | |
except: | |
print("Not availaible in kindle") | |
else: | |
print("Kindle price :",a) | |
try: | |
b=tag.find_next('a',{"title":"Paperback"}).find_next('span',{"class":"a-size-base a-color-price s-price a-text-bold"}).get_text() | |
except: | |
print("Price of paperback was'nt scraped") | |
else: | |
print("Paperback price :",b) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment