catty-scrape.py

#!/usr/bin/env python

import codecs
import sys
import urllib2
from bs4 import BeautifulSoup

sys.stdout = codecs.getwriter('utf8')(sys.stdout)

page_url = 'https://iscrapapp.com/yards/us-pennsylvania-catasauqua-catasauqua-scrap-yard-premium/pricing/'
hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Referer': 'https://cssspritegenerator.com',
        'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
        'Accept-Encoding': 'none',
        'Accept-Language': 'en-US,en;q=0.8',
        'Connection': 'keep-alive'}

request = urllib2.Request(page_url, headers = hdr)

page = urllib2.urlopen(request)

soup = BeautifulSoup(page, 'html5lib')

print(soup.find("div", {"class": "pricing-top"}))

for pricing_table in soup.find_all("table", {"class": "pricing-table"}):
    table_name = pricing_table.parent.find_previous_sibling("div", {"class": "yard-section-header"}).find("h3").get_text()
    print("<h3>" + table_name + "</h3>")
    print("<table><tr><th>Material Name</th><th>Material Price</th>")
    for row in pricing_table.find_all('tr'):
        material_name = row.find("td", {"class": "material-name"})
        material_price = row.find("td", {"class": "material-price"})
        if material_name and material_price:
            print("<tr><td class=\"material-name\">")
            print(material_name.get_text())
            print("</td><td class=\"material-price\">")
            print(material_price.get_text())
            print("</td></tr>")
    print("</table>")