# coding=utf-8import requests
headers ={
"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36"}
url ="https://www.baidu.com/s?wd={}".format("python")
r = requests.get(url,headers=headers)print(r.status_code)print(r.request.url)print(r.content)
# coding=utf-8import requests
import sys
# 需要带参数需要获取的贴吧名称运行,如:pythonclassTiebaSpider:def__init__(self, tieba_name):
self.tieba_name = tieba_name
# 构建url的基本格式.
self.url_temp ="https://tieba.baidu.com/f?kw="+ tieba_name +"&ie=utf-8&pn={}"
self.headers ={
"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36"}# 构建每一个的np数值->数值.defget_url_list(self):return[self.url_temp.format(i *50)for i inrange(1000