將爬取下來的內容儲存到本地

import re
import time
import urllib

import requests
from lxml import etree


class ImmgeSpider:
    def __init__(self):
        self.headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; The World)"}
        # self.headers = {"User_Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36"}
 



    # 獲取所有帖子URL列表
    def getPageUrl(self, url):
        # 獲取貼吧頁面的html
        res = requests.get(url, headers=self.headers)
        print(url)
        res.encoding = "utf-8"
        html = res.text
        # print(html)
        # 提取頁面中所有帖子的url
        # parseHtml = etree.HTML(html)
        # t_list = parseHtml.xpath('//li[@class=" j_thread_list clearfix"]/div/div[2]/div[1]/div[1]/a/@href')
 

        p = re.compile('<div class="threadlist_title pull_left j_th_tit ">.*?<a rel="noreferrer" href="(.*?)" title', re.S)
        t_list = p.findall(html)
        print(t_list)

        for t_link in t_list:
            t_url = "http://tieba.baidu.com" + t_link
            self.getImageUrl(t_url)

    
 
# 獲取每個帖子中圖片的url列表
    def getImageUrl(self, t_url):
        # 獲取每個帖子的響應html
        res = requests.get(t_url, headers = self.headers)
        res.encoding = "utf-8"
        html = res.text
        parseHtml = etree.HTML(html)
        img_list = parseHtml.xpath('//*[@class="d_post_content j_d_post_content  clearfix"]/img/@src | //embed/@data-video')
        print(img_list)

        for img_link in img_list:
            self.writeImage(img_link)

    # 儲存圖片
    def writeImage(self, img_link):
        time.sleep(2)
        # 獲取每張圖片的二進位制
        res = requests.get(img_link, headers=self.headers)
        res.encoding = "utf-8"
        html = res.content
        # 儲存到本地(以圖片的後12位為檔名)
        filename = img_link.split("/")[-1]
        if "?" in filename:
            filename = filename.split("?")[-1]
        with open("圖片/"+ filename, 'wb') as f:
            f.write(html)
            print(filename, "下載成功")

    # 主函式
    def workOn(self):
        name = input("請輸入貼吧名：")
        start = int(input("請輸入起始頁："))
        end = int(input("請輸入結束頁："))
        for pn in range(start, end+1):
            pn = (pn-1) * 50
            kw = {"kw": name}
            kw = urllib.parse.urlencode(kw)
            fullurl = "http://tieba.baidu.com/f?" + kw + "&ie=utf-8&pn=" + str(pn)
            # fullurl = "http://tieba.baidu.com/f?kw=%E6%A0%A1%E8%8A%B1&ie=utf-8&pn=50"
            # 直接呼叫類內函式
            self.getPageUrl(fullurl)


if __name__ == '__main__':
    spider = ImmgeSpider()
    spider.workOn()