'''目标网站：https://www.1ppt.com/moban/需求：1、用多线程爬取前10页模板名字和模板详情页链接2、把模板名字和模板详情页链接保存到模板.csv文件里面https://www.1ppt.com/moban/ppt_moban_2.htmlhttps://www.1ppt.com/moban/ppt_moban_3.html'''header = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'}import requestsimport threading#导入多线程库import csvfrom queue import Queue #导入队列的库# from bs4 import BeautifulSoupfrom lxml import htmlimport timeprint(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime()))etree = html.etreeclass One(threading.Thread): la7 = [] def __init__(self, url, data): super().__init__() self.zhen2 = url self.chao3 = data def run(self): while True: if self.zhen2.empty(): break else: zhen3 = self.zhen2.get() # print(zhen3) tm = requests.get(zhen3, headers=header) tm.encoding = 'gb2312' td = tm.text # print(td) la2 = etree.HTML(td) la3 = la2.xpath('//ul[@class="tplist"]/li') for t in la3: la6 = {} la5 = t.xpath('./a/img/@src')[0] la4 = t.xpath('./a/img/@alt')[0] la6['模板名字'] = la4 la6['模板地址'] = la5 self.la7.append(la6) with open('模板.csv', 'w', encoding='utf-8', newline='')as f: write = csv.DictWriter(f, fieldnames=['模板名字', '模板地址']) write.writeheader() write.writerows(self.la7) print(time.strftime('%Y-%m-%d %H:%M:%S', time.localtime())) # la = BeautifulSoup(td, 'lxml') #转为它这个对象 # a = la.find('ul', class_="tplist") # jiem2 = a.find_all('li') # print(len(jiem2))if __name__ == '__main__': #程序主入口 #1、创建url队列 tom = Queue() #2、创建一个放模板名字和模板的链接的队列 jemi = Queue() tom.put('https://www.1ppt.com/moban/') #生产者 for i in range(2, 11): look = f'https://www.1ppt.com/moban/ppt_moban_{i}.html' tom.put(look) # print(tom) for i in range(3): #分为三个进程 t = One(tom, jemi) t.start() #启动进程 # t.join()