python多线程爬虫 和讯期货 标题和内容页的URL

#coded by 伊玛目的门徒
import re
import requests
import time
from bs4 import BeautifulSoup

urllist=[]
titlelist=[]

start = time.clock()  # 计时-开始



from concurrent.futures import ThreadPoolExecutor


header={'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.XXXX.XXX Safari/537.36'}


def do(i):
    try:
        cd=[]
        html=requests.get('http://futures.hexun.com/domestic/index-'+str(i)+'.html',headers=header)

        html.encoding='gbk'

        Soup = BeautifulSoup(html.text, "lxml")
        #ab=Soup.select('li a[target="_blank"]')
        ab=Soup.select('div.temp01 ul li a[target="_blank"]')

        for x in range(len(ab)):
            if (x % 2) == 1:
                cd.append (ab[x])

        print ('-----------------')

        pattern = re.compile(r'<a href="(.*?)" target="_blank">',re.S)   # 查找数字
        result1 = pattern.findall(str(cd))
        pattern2 = re.compile(r'target="_blank">(.*?)</a>',re.S)
        result2 = pattern2.findall(str(cd))
        print (result1)
        urllist.extend(result1)
        print (result2)
        titlelist.extend(result2)


        list1.remove(i)






    except:
        pass



# 多线程
def multithreading():
    sum=0

    while len(list1)>0:
        with ThreadPoolExecutor(max_workers=10) as executor:
            for result in executor.map(do, list1):
                sum+=1

    return sum




list1=list(range(1,393,1))

sum=multithreading()
print ('还剩下{}页'.format(list1))



end = time.clock()  # 计时-结束
print (("爬取完成 用时:"))
print ((end - start))


print ('总爬取 %d 页 '%(sum))

while None in titlelist:
    titlelist.remove(None)

while None in urllist:
    urllist.remove(None)

print (titlelist)

print (urllist)


'''
#可作为TXT输出
with open("test.txt","w") as f:
        for thing in urllist:

            f.write(thing)
            f.write('\r\n')
'''

演示视频:

https://www.bilibili.com/video/av80003976/

python多线程爬虫和讯网 标题和正文URL效果展示

 

后续可看 

https://blog.csdn.net/qq_37195257/article/details/103643238

  • 0
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值