python爬虫---多线程爬取腾讯招聘数据【晋级版】

多线程快速爬取

import time

from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
import os
import threading

class Tencent(threading.Thread):
    def __init__(self,page):
        super().__init__()
        self.page = page
    def save_to_html(self,html_str,filename):
        dirname = os.path.dirname(filename)
        if not os.path.exists(dirname):
            os.mkdir(dirname)
        with open(filename,'w',encoding='utf-8') as fp:
            fp.write(html_str)
        print('下载完成！',filename)

    def get_content_by_selenium(self,url):
        driver = webdriver.PhantomJS()
        wait = WebDriverWait(driver,20)
        #请求
        driver.get(url)
        #等待
        wait.until(EC.presence_of_all_elements_located((By.XPATH,'//div[@class="recruit-list"]')))
        #获取页面内容
        html_str = driver.page_source
        return html_str

    def download(self,i):
        base_url = 'https://careers.tencent.com/search.html?index=%s'
        html_str = self.get_content_by_selenium(base_url %i)
        self.save_to_html(html_str,'./tencent/{}.html'.format(i))
    def run(self):
        self.download(self.page)
if __name__ == '__main__':
    start = time.time()
    #用第一种创建线程来开启多线程
    crawl_list = []
    for i in range(1, 20):
        # download(i)
        #用这种方法开启线程，弊端很大
        #任务数就是线程数，这样如果任务比较大，容易造成崩溃。
        #任务无法按照顺序来执行
        # t = threading.Thread(target=download,args=(i,))
        t = Tencent(i)
        t.start()
        crawl_list.append(t)

    #阻塞主线程，我们join方法
    for t in crawl_list:
        t.join()#阻塞当前线程，指导t线程运行结束
    print(time.time()-start)#21.61223602294922