python3爬虫例子01（获取个人博客园的粉丝）

#!/usr/bin/env python
# -*- coding:UTF-8 -*-

import requests
from selenium import webdriver
from bs4 import BeautifulSoup
import re
import time


class GetFansName:
    #初始化各配置项数值
    def __init__(self, profiles, url, ses, sleepTime, fansNameFile):
        self.profiles = profiles
        self.url = url
        self.ses = ses
        self.sleepTime = sleepTime
        self.fansNameFile = fansNameFile

    def get_cookies(self):
        try:
            #加载配置文件
            profiles = webdriver.FirefoxProfile(self.profiles)

            driver = webdriver.Firefox(profiles)

            driver.get(self.url+"/followers")

            time.sleep(self.sleepTime)

            #获取COOKIES
            cookies = driver.get_cookies()

            # print(cookies)

            driver.quit()

            return cookies
        except Exception as msg:
            print("get_cookies error:%s"%str(msg))


    def add_cookies(self,cookies):
        try:
            c=requests.cookies.RequestsCookieJar()
            for i in cookies:
                c.set(i["name"],i["value"])

            #更新COOKIES
            self.ses.cookies.update(c)
        except Exception as msg:
            print("add_cookies error:%s"%str(msg))


    def get_fansNum(self):
        try:
            #发送访问粉丝的请求
            fansres = self.ses.get(self.url+"/relation/followers")

            fanssoup = BeautifulSoup(fansres.content,"html.parser")

            #获取粉丝数量
            tempfansnum = fanssoup.find_all(class_="current_nav")

            # print(tempfansnum[0].string)

            strfansnum = re.findall(u"我的粉丝\((.+?)\)",tempfansnum[0].string)
            print(u"我的粉丝数量:%s"%str(strfansnum[0]))

            #粉丝分页数量
            fansnum = int(int(strfansnum[0])/45)+1

            print(u"总的分页:%s"%str(fansnum))

            return fansnum
        except Exception as msg:
            print("get_fansNum error:%s"%str(msg))
            return 1


    def get_fansName(self,fansnum):
        try:
            #判断有几页粉丝，然后分别去处理
            if fansnum <=1:
                url_page=self.url+"/relation/followers"
            else:
                url_page=self.url+"/relation/followers?page=%s"%str(fansnum)

            print("正在抓取页面:%s"%url_page)

            fansnameres=self.ses.get(url_page,verify=False)

            fansnamesoup=BeautifulSoup(fansnameres.content,"html.parser")

            fansnames=fansnamesoup.find_all(class_="avatar_name")

            #将粉丝名字写入文件
            for fansname in fansnames:
                name=fansname.string.replace("\n"," ").strip(" ")

                with open(self.fansNameFile,'a',encoding="utf-8") as file:
                    file.write(name+"\n")
        except Exception as msg:
            print("get_fansName error:%s"%str(msg))


if __name__ == '__main__':

    #FireFox profile文件路径
    profiles = r"C:\Users\Administrator\AppData\Roaming\Mozilla\Firefox\Profiles\wv0f79j4.default"

    #要抓取的粉丝的URL
    url = "https://home.cnblogs.com/u/NiceTime"

    #存放粉丝名字的文件
    fansNameFile = "fansNameFile.txt"

    #打开浏览器后，等待的时间，单位秒
    sleepTime = 5

    #获取当前请求的会话
    ses = requests.session()

    fansName = GetFansName(profiles, url, ses,sleepTime,fansNameFile)

    cookies = fansName.get_cookies()

    fansName.add_cookies(cookies)

    fansNums = fansName.get_fansNum()

    for fansNum in range(1, fansNums+1):
        fansName.get_fansName(fansNum)