Python XPath抓取小说《三国演义》 《三》 多线程简单实例

 

增加多线程抓取数据，增加url判断，若数据已抓取，不在重复抓取  （可参考URL管理器）

需要再添加上队列,否则全开

from lxml import etree
import requests
import time
import os
import random
import urllib3
from multiprocessing import Pool
import _thread
import threading


def getHeaders():

    #随机获取一个headers

    user_agents = ['Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1',
                   'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
                   'Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11',
                   'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
                   'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36',
                   'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36',
                   'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36',
                   'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36',
                   'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36',
                   'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36',
                   'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0) Gecko/20100101 Firefox/17.0.6',
                   'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1468.0 Safari/537.36',
                   'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2224.3 Safari/537.36',
                   'Mozilla/5.0 (X11; CrOS i686 3912.101.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36'
                   ]
    headers = {'User-Agent': random.choice(user_agents),'Connection':'close'}
    return headers

"""
request请求头
"""
def getRequestHtml(target):
    req = ""
    try:

        req = requests.get(url = target,headers = getHeaders(),verify=False,proxies=None)
        req.encoding = "gb2312"
        requests.adapters.DEFAULT_RETRIES = 5
        urllib3.disable_warnings()
        html = req.text
        return html
    except requests.exceptions.ConnectionError:
        req.status_code = "Connection refused"


"""
获取章节列表和地址
"""
def  getContents(target,filePath):

    html = getRequestHtml(target)
    bookdata = etree.HTML(html)
    table_list = bookdata.xpath('//table[9]//tr[1]//td[2]//table[4]//tr[1]//td[1]//table[1]//a')
    return table_list

"""
获取小说内容
"""
def getContent(filePath, title,target):
    html = getRequestHtml(target)
    bookdata = etree.HTML(html)
    table_list = bookdata.xpath('//table[5]//tr[1]//td[2]//text()')

    saveData(filePath, title, table_list)


"""
将小说内容写入到文件
"""


def saveData(filepath, name, text):

    isExists = os.path.exists(filepath)

    if not isExists:
        os.makedirs(filepath)

    url = filepath+name+".txt"
    with open(url, mode="w", encoding="UTF-8") as f:
        f.writelines(text)
        f.write('\n\n')



class myThread(threading.Thread):
    def __init__(self,filePath,title,url):
        threading.Thread.__init__(self)
        self.filePath = filePath
        self.title = title
        self.url = url
    def run(self):

        getContent(self.filePath, self.title, self.url)


if __name__ == '__main__':
    #三国演义 目录地址
    target = "https://www.kanunu8.com/files/old/2011/2447.html"
    filePath = "D:\\小说\\三国演义\\"
    #获取目录列表和地址列表
    title_list = getContents(target,filePath)

    t_start = time.time()
    threadlist = []
    for t in title_list:
        title = t.text
        url = "https://www.kanunu8.com/files/old/2011/"+t.get('href')
        print(title,url)

        #先判断是否已经抓取过了该页面
        isEx = os.path.isfile(filePath+title+".txt")
        if not isEx:
            try:
                thread1 = myThread(filePath, title, url)
                thread1.setDaemon(True)  # 设置守护线程，父线程会等待子线程执行完后再退出
                thread1.start()
                threadlist.append(thread1)
            except:
                print("无法启动线程")
        else:
            print("该文件已经存在 不需要再次抓取")

    for tt in threadlist:
        tt.join()

    t_end = time.time()

    print('抓取本书耗时= %s' % (t_end - t_start))