【Python】百度搜索

fromurllibimportrequest

importre

url="http://www.baidu.com/s?wd="

key="python"#搜索关键词

pageCount=#搜索记录条数

#对关键词进行编码，因为url中需要对中文等进行处理

key_code=request.quote(key)

#带检索关键词的url

url=url+key_code+"&ie=utf-8&pn="

#请求头

headers={

'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36'

}

defgetInfosByPage(page):

req=request.Request(url+str(page*10-10),headers=headers)

res=request.urlopen(req)

html=res.read().decode("utf-8","ignore")

ifpage==1:

patPage="百度为您找到相关结果约(.*?)个"

globalpageCount

pageInfo=re.findall(patPage,html)[]

pageCount=int(pageInfo.replace(",",""))

ifpageCount

return

pat='data-tools="{"title":"(.*?)","url":"(.*?)"}"'

pat=pat.replace('"','[\'"]?')

datas=re.findall(pat,html,re.S|re.M)

fordataindatas:

print("标题："+data[])

print("网址："+data[1])

print("="*100)

if__name__=="__main__":

forpageinrange(1,10):

getInfosByPage(page)