headers = {'User-Agent' : 'Mozilla/5.0 (Linux; Android 4.2.1; en-us; Nexus 4 Build/JOP40D)'' AppleWebKit/535.19 (KHTML, like Gecko) Chrome/18.0.1025.166 Mobile Safari/535.19'}headers = {'User-Agent': 'Chrome/68.0.3440.106', 'Accept-Encoding': 'gzip, deflate', 'Accept': '*/*', 'Connection': 'keep-alive', 'Content-Length': '18', 'Content-Type': 'application/x-www-form-urlencoded'}

#调用模块的UserAgent类方法
from fake_useragent import UserAgent#实例化类方法
user_agent = UserAgent()#选择chrome浏览器为User-Agent的值
headers = {'User-Agent':user_agent.chrome}#选择ie浏览器为User-Agent的值
headers = {'User-Agent':user_agent.ie}#选择firefox浏览器为User-Agent的值
headers = {'User-Agent':user_agent.firefox}#随机选择一款浏览器为User-Agent的值
headers = {'User-Agent':user_agent.random}

from requests.exceptions import ReadTimeouttry:response = requests.get(url, headers=headers, timeout=0.5)if response.status_code == 200:return response.textreturn 404
except ReadTimeout:print('timeout')
except Exception as e:print(e)

import reresponse = """<div class="c-span18 c-span-last"><em>太阳</em>是<em>太阳</em>系的中心天体，占有<em>太阳</em>系总体质量的99.86%。 </div>"""
partten = r'<div class="c-span18 c-span-last">([sS]*?)</div>'
data = re.findall(partten, response,)
print(data)
data_clean = re.sub(r'<em>|</em>', '', data[0])
print(data_clean)

['<em>太阳</em>是<em>太阳</em> 系的中心天体，占有<em>太阳</em>系总体质量的99.86%。']
太阳是太阳系的中心天体，占有太阳系总体质量的99.86%。

import urllib.request
import re
from fake_useragent import UserAgent
import requests
from requests.exceptions import ReadTimeout
import osuser_agent = UserAgent()
headers = {"User-Agent": user_agent.chrome,}
def get_html(url, req=None):if req:url = url + reqelse:url = urltry:response = requests.get(url, headers=headers)if response.status_code == 200:#print(response.text)return response.textreturn 404except ReadTimeout:print('timeout404')except Exception as e:print(e)def get_request(response):if response == 404:return '服务器响应失败！'else:try:partten = r'<img width="220" height="220" data-img="1" data-lazy-img="//(.+?.jpg)">'data = re.compile(partten).findall(response)return dataexcept IndexError:print('未搜到有用信息')
def output(data):if not os.path.exists('texts'):os.mkdir('texts')for index, inf in enumerate(data):image_url = 'https://' + infimage_byte = requests.get(url=image_url, headers=headers).contentwith open("./texts/{}.jpg".format(index),'wb') as f:f.write(image_byte)print('n第{}张图片已下载保存成功...'.format(index))print('n总共{}张图片已成功下载至texts文件夹中'.format(len(data)))
def main(req):url = 'https://list.jd.com/list.html?cat=9987,653,655&page='html = get_html(url, req)data = get_request(html)output(data)if __name__ == '__main__':req = input('请输入要下载的页码: ')main(req)