智能解析文章

auto_extract.py

import requests
import json
headers = {
    'Accept': 'application/json',
    'Referer': 'https://scrapinghub.com/autoextract',
    'Origin': 'https://scrapinghub.com',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36',
    'Sec-Fetch-Mode': 'cors',
    'Content-Type': 'application/json',
}
url = "http://www.bjd.com.cn/jx/tp/201909/03/t20190903_11104419.html"
data = json.dumps({"url": url, "page_type": "article"})

response = requests.post('https://xod-beta-forwarder.scrapinghub.com/extract', headers=headers, data=data)
from pprint import pprint

pprint(response.text)