Created
April 26, 2017 17:41
-
-
Save jeremyboggs/1cf348d13eea9c0b46553e6a2bbb61f0 to your computer and use it in GitHub Desktop.
Scrape locally-saved Pinterest web pages
This file contains hidden or 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
#!/usr/bin/env python | |
import os | |
import sys | |
import urllib2 | |
from bs4 import BeautifulSoup | |
# Base URL for Pinterest. | |
base_url = 'http://pinterest.com' | |
html_file = sys.argv[1] | |
file_in = open(html_file,'r') | |
newfile = os.path.splitext(html_file)[0] + '.txt' | |
with open (newfile, 'w') as file_out: | |
soup = BeautifulSoup(file_in,'html.parser') | |
# Find all the articles on each page. | |
for pin in soup.find_all('div', {'class': ['PinRep','GrowthUnauthPin_brioPin']}): | |
title = pin.h3 | |
if title is None: | |
title = '' | |
else: | |
title = title.contents[0].encode('utf-8') | |
description = pin.p | |
if description is None: | |
description = '' | |
elif len(description.contents) < 1: | |
description = '' | |
else: | |
description = description.contents[0].encode('utf-8') | |
file_out.write(title + description) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment