PHP
·
发表于 5年以前
·
阅读量:8398
#抓取Top100网 (成功)
from urllib.request import urlopen
'''
https://maoyan.com/board/4?offset=10
https://maoyan.com/board/4?offset=20
https://maoyan.com/board/4?offset=30
...
https://maoyan.com/board/4?offset=90
'''
def get_one_page(index):
url = 'https://maoyan.com/board/4?offset=%d'%(index*10)
#另一种方式: url = 'https://maoyan.com/board/4?offset={}/'.format(index * 10)
#字符串的格式化处理 {} 占位符 使用format方式格式化字符串
response = urlopen(url)
return response.read().decode()
def save_one_page(index,html):
#将数据保存到文件中
# 文件名 maoyan_TOP100_page_inedx.html
# 文件存到什么地方
filename = 'maoyan\\TOP100_page_{}.html'.format(index+1)
'''
打开文件 打开方式:r(以字符串的方式只读),w(以字符串的方式只写),a(以字符串的方式追加)
rb(以二进制只读),wb(以二进制只写),ab(以二进制追加)
'''
#file = open(filename,'w',encoding = 'utf-8')
#file.write(html)
#file.close()
with open(filename,'w',encoding='utf-8') as file:
file.write(html)
pass
if __name__ == '__main__':
for index in range(0,10):
html = get_one_page(index)
save_one_page(index,html)
#__name__ 内置变量
#当执行当前文件时,__name__==_main_
#当当前文件时被其他文件引用时,__name__==模块名