2021-06-29

爬虫向百度提交关键词的方法

#encoding = “utf-8”
import requests

kv = {

'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36',

"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3"

  }

kw = {‘wd’ : “python”}

def getHTMLText(url):
try:
#r = requests.get(url)
#r = requests.get(url, headers = kv)
#r = requests.get(url, data=payload)
r = requests.get(“http://www.baidu.com/s”, params=kw, headers = kv)
print(r.status_code)
#print(r.encoding)
print(r.request.url)
r.raise_for_status()
r.encoding = r.apparent_encoding
#return r.text[:2000]
return len(r.text)
except:
return “产生异常”

if name == “main”:
#url = “https://item.jd.com/100011742101.html”
url = “http://www.baidu.com/s”
print(getHTMLText(url))