简单的爬虫

对某一视频共享网站电影名进行爬取

# Author：Winter Liu
import time
import urllib.request
import re

start_time = time.time()
html_start = 'https://yanghuanyu.com/dy'
result = []
for i in range(2,31):
    response = urllib.request.urlopen(html_start)
    buff = response.read()
    html = buff.decode('utf-8')
    # with open('hpage.txt','w',encoding='UTF-8') as f:
    #     f.write(html)
    print(html_start)
    data = re.findall(r'[.+][dddd][.+][.+]', html)
    data = list(set(data))
    print(data)
    result.extend(data)
    html_start = "https://yanghuanyu.com/dy/page/"+str(i)
print(len(result))
print(result)

end_time = time.time()
print(end_time  - start_time)