爬取前三页的数据
第一次写的代码:
# 综合项目实战:爬取搜狗,知乎某一词条对应的某一范围页码的数据
# 分析下爬取第一页的url和第二页的url,get请求参数中只有page在变,把url固定,变量封装
import requests
url='http://zhihu.sogou.com/zhihu?'
headers={
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"
}
for page in range(1,3):
params={
'query':'人工智能',
'page':page,
'ie':'utf-8'
}
response = requests.get(url=url,params=params,headers=headers)
page_data = response.text
with open(str(page)+ '.html','w',encoding='utf-8') as f: