python 多线程爬虫

环境搭建

1. requests：获取数据
2. lxml：解析数据

 

本次爬去糗事百科，爬取地址：http://www.qiushibaike.com/8hr/page/1/

python3 代码示例

import requests
import threading
from queue import Queue
from lxml import etree
import json

class Thread_Crawl(threading.Thread):
    def __init__(self,threadName,pageQueue,dataQueue):
        super().__init__()
        self.threadName = threadName
        self.pageQueue = pageQueue
        self.dataQueue = dataQueue
        self.headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'}

    def run(self):
        print("%s启动了" % self.threadName)
        while not self.pageQueue.empty():
            url = self.pageQueue.get()
            res = requests.get(url, headers=self.headers).text
            if not self.dataQueue.full():
                self.dataQueue.put(res)
        print("%s结束了" % self.threadName)

class Thread_Parse(threading.Thread):
    def __init__(self,threadName,dataQueue,lock,file):
        super().__init__()
        self.threadName = threadName
        self.dataQueue = dataQueue
        self.lock = lock
        self.file = file

    def run(self):
        print("%s启动了"%self.threadName)
        while not self.dataQueue.empty():
            html = etree.HTML(self.dataQueue.get())
            self.parse(html)
        print("%s结束了" % self.threadName)

    def parse(self,html):
        print(html.text)
        node_list = html.xpath('//div[contains(@id, "qiushi_tag")]')
        for node in node_list:
            username = node.xpath('./div/a/@title')[0]
            image = node.xpath('.//div[@class="thumb"]//@src'  )  # [0]
            content = node.xpath('.//div[@class="content"]/span')[0].text
            zan = node.xpath('.//i')[0].text
            comments = node.xpath('.//i')[1].text
            items = {
                "username" : username,
                "image" : image,
                "content" : content,
                "zan" : zan,
                "comments" : comments
            }
            with self.lock:
                self.file.write(json.dumps(items) + "\n")

if __name__ == "__main__":
    pageQueue = Queue(11)
    dataQueue = Queue()
    lock = threading.Lock()
    file = open("data.json", "a")

    for x in range(1,3):
        url = 'http://www.qiushibaike.com/8hr/page/' + str(x) + '/'
        pageQueue.put(url)

    CrawlList = ['采集线程1','采集线程2','采集线程3']
    for crawlName in CrawlList:
        thread = Thread_Crawl(crawlName,pageQueue,dataQueue)
        thread.start()
        thread.join()

    ParseList = ['解析线程1', '解析线程2', '解析线程3']
    for parseName in ParseList:
        thread = Thread_Parse(parseName, dataQueue,lock,file)
        thread.start()
        thread.join()

    with lock:
        file.close()

View Code