python_apps/crwlers/graingerGetSpecs.py
2023-11-03 14:49:12 +09:00

34 lines
1.1 KiB
Python

import requests, bs4, urllib, sys, re, math
url = str(sys.argv[1]);
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36',
'Accept-Encoding': 'gzip, deflate, br',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Upgrade-Insecure-Requests': '1',
'save-data': 'on',
'Host': 'www.grainger.com'
}
resp = requests.get(url, headers = headers)
resp.raise_for_status()
resp.encoding='UTF-8'
html = resp.text
bs = bs4.BeautifulSoup(html, 'html.parser')
prdName = bs.select('div#productPage div h1.productName')[0].getText().strip()
zoomIMG = bs.select('img#mainImageZoom')[0]['data-blzsrc']
zoomIMG = 'https:' + re.sub('\$mdmain\$','$zmmain$',zoomIMG)
techSpecsName = bs.select('div.techSpecsTable ul li span.specName')
techSpecsValue = bs.select('div.techSpecsTable ul li span.specValue')
for i in range(len(techSpecsName)) :
name = techSpecsName[i].getText().strip()
value = techSpecsValue[i].getText().strip()
if name != '' :
print(prdName + "\t" + url + "\t" + name + "\t" + value)