糗百爬虫

#coding:utf-8
import requests
import json
from lxml import etree
import threading
from queue import Queue
class QiushiSpide(object):
    def __init__(self):
        self.url_tmp = "https://www.qiushibaike.com/8hr/page/{}/"
        self.header = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.96 Safari/537.36"}
        self.pre_url = "https://www.qiushibaike.com"
        self.url_queue = Queue()
        self.html_queue = Queue()
        self.content_queue = Queue()

    def get_url_list(self):
        for i in range(1,14):
            self.url_queue.put(self.url_tmp.format(i))
        print(self.url_queue.qsize())
        # return [self.url_tmp.format(i) for i in range(1,14)]

    def parse_url(self):
        while True:
            url = self.url_queue.get()
            print(url)
            response = requests.get(url, self.header)
            self.html_queue.put(response.content.decode())
            self.url_queue.task_done()
            print("url_queue 完成一个")
            # return response.content.decode()

    def get_content_list(self):
        while True:
            html_str = self.html_queue.get()
            html = etree.HTML(html_str)
            li_list = html.xpath("//li[contains(@class,'item typs_')]")
            content_list=[]
            for li in li_list:
                item = {}
                img_list = li.xpath(".//a[contains(@class,'recmd-left')]")
                for img in img_list:
                    item["img_url"] = "https:" + img.xpath("./img/@src")[0] if len(img.xpath("./img/@src"))>0 else None
                div_list = li.xpath(".//div[@class='recmd-right']")
                for div in div_list:
                    item["text"] = div.xpath("./a/text()")[0] if len(div.xpath("./a/text()"))>0 else None
                    item["a_href"] = self.pre_url + div.xpath("./a/@href")[0] if len(div.xpath("./a/@href"))>0 else None
                    item["smile_num"] = div.xpath(".//div[@class='recmd-num']/span[1]/text()")[0] if len(div.xpath(".//div[@class='recmd-num']/span[1]"))>0 else None
                    item["comment_num"] = div.xpath(".//div[@class='recmd-num']/span[4]/text()")[0] if len(div.xpath(".//div[@class='recmd-num']/span[4]"))>0 else None
                content_list.append(item)
            self.content_queue.put(content_list)
            self.html_queue.task_done()
            print("html_queue 完成一个")
            # return content_list

    def save_content(self):
        while True:
            content = self.content_queue.get()
            with open("糗百多线程.txt",'a',encoding='utf-8') as f:
                f.write(json.dumps(content,ensure_ascii=False,indent=2))
                f.write("\n")
            self.content_queue.task_done()

    def run(self):
        # url_list = self.get_url_list()
        # for url in url_list:
        #     print(url)
        #     html_str = self.parse_url(url)
        #     content = self.get_content_list(html_str)
        #     self.save_content(content)
        t_list = []
        self.get_url_list()
        for i in range(4):
            p = threading.Thread(target=self.parse_url)
            t_list.append(p)
        print("添加parse_url线程结束")
        for i in range(4):
            g = threading.Thread(target=self.get_content_list)
            t_list.append(g)
        print("添加get_content_list线程结束")
        s = threading.Thread(target=self.save_content)
        t_list.append(s)
        for t in t_list:
            t.setDaemon(True) #守护线程，该线程不重要，主线程结束，子线程结束
            t.start()

        for q in [self.url_queue,self.html_queue,self.content_queue]:
            q.join() #让主线程等待阻塞，等待队列的任务执行完了后再 完成
        print("主线程end")
if __name__ == "__main__":
    q = QiushiSpide()
    q.run()

 

转载于:https://www.cnblogs.com/dreamhai/p/10575359.html