import requests
from bs4 import BeautifulSoup
'''
It's a web crawler working in ebay, collecting every single item data
'''
def ebay_spider(max_pages):
page = 1
while page <= max_pages:
url = 'http://www.ebay.co.uk/sch/Apple-Laptops/111422/i.html?_pgn=' \
+ str(page)
source_code = requests.get(url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for link in soup.findAll('a', {'class': 'vip'}):
href = 'http://www.ebay.co.uk' + link.get('href')
title = link.string
get_single_item_data(href)
page += 1
def get_single_item_data(item_url):
source_code = requests.get(item_url)
plain_text = source_code.text
soup = BeautifulSoup(plain_text)
for item_name in soup.findAll('h1', {'id': "itemTitle"}):
print(item_name.string)
ebay_spider(3)
Blockquote And the error say that : https://i.sstatic.net/zbJ6y.jpg
I tried to fix it but it seems not to work, so any tips/answers how to fix it?EDIT: Sorry everyone for faulty title and tag, everything was fixed.
When you're trying to make a BeatifulSoup object in line, do instead this:
soup = BeautifulSoup(plain_text)
This:
soup = BeautifulSoup(plain_text, 'html.parser')
Note: your problem refers to bs4 module, not requests.