Python: using regex to pull "product_id' from html javascript -
i trying pull piece out of javascript - "product_id' of product ids , assign them object or list
html -
<div class="product-options" id="product-options-wrapper"> <script type="text/javascript"> try { var changeconfigurablestatus = true; var ststatus = new stockstatus({"242":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92964"},"246":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92965"},"363":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92966"},"248":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92967"},"243":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92968"},"368":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92969"},"244":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92970"},"247":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92971"},"79":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92972"},"249":{"is_in_stock":true,"custom_status_icon":"","custom_status":"","product_id":"92973"}}); } this script @ -
import requests bs4 import beautifulsoup bs import random import re session = requests.session() product_url = 'http://www.randomsite.com' response = session.get(product_url) soup = bs(response.text,'lxml') div = soup.find_all("div",{"class":"attribute-item"}) # select divs .attribute-item class all_sizes = [x['data-value'] x in div] # extract 'data-value' attribute divs .attribute-item size_chosen = random.choice(all_sizes) print(all_sizes) print(size_chosen) i have been informed need "get text inside script using soup.find('script').text, after need regex pick out specific text looking for. " not sure begin in obtaining this. or how implement line code even.
Comments
Post a Comment