多线程爬虫
糗事百科
1 import requests 2 from lxml import etree 3 from queue import Queue 4 import threading 5 6 7 class Qiubai: 8 def __init__(self): 9 self.temp_url = "https://www.qiushibaike.com/8hr/page/{}/" 10 self.headers= {"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X \ 11 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.186 Safari/537.36"} 12 self.url_queue = Queue() 13 self.html_queue = Queue() 14 self.content_list_queue = Queue() 15 16 def get_url_list(self):#获取url列表 17 for i in range(1,14): 18 self.url_queue.put(self.temp_url.format(i)) 19 20 def parse_url(self): 21 while True: #在这里使用，子线程不会结束，把子线程设置为守护线程 22 url = self.url_queue.get() 23 # print(url) 24 response = requests.get(url,headers=self.headers) 25 self.html_queue.put(response.content.decode()) 26 self.url_queue.task_done() 27 28 29 def get_content_list(self): #提取数据 30 while True: 31 html_str = self.html_queue.get() 32 html = etree.HTML(html_str) 33 div_list = html.xpath("//div[@id='content-left']/div") 34 content_list = [] 35 for div in div_list: 36 content = {} 37 content["content"] = div.xpath(".//div[@class='content']/span/text()") 38 content_list.append(content) 39 self.content_list_queue.put(content_list) 40 self.html_queue.task_done() 41 42 def save_content_list(self): 43 while True: 44 content_list = self.content_list_queue.get() 45 for content in content_list: 46 print(content) # 此处对数据进行保存操作 47 self.content_list_queue.task_done() 48 49 50 def run(self): 51 thread_list = [] 52 #1.url_list 53 t_url = threading.Thread(target=self.get_url_list) 54 thread_list.append(t_url) 55 #2.遍历，发送请求， 56 for i in range(3): #三个线程发送请求 57 t_parse = threading.Thread(target=self.parse_url) 58 thread_list.append(t_parse) 59 #3.提取数据 60 t_content = threading.Thread(target=self.get_content_list) 61 thread_list.append(t_content) 62 #4.保存 63 t_save = threading.Thread(target=self.save_content_list) 64 thread_list.append(t_save) 65 66 for t in thread_list: 67 t.setDaemon(True) #把子线程设置为守护线程，当前这个线程不重要，主线程结束，子线程技术 68 t.start() 69 70 for q in [self.url_queue,self.html_queue,self.content_list_queue]: 71 q.join() #让主线程阻塞，等待队列的计数为0， 72 73 print("主线程结束") 74 75 if __name__ == '__main__': 76 77 qiubai = Qiubai() 78 qiubai.run()
