python爬取豆瓣出版社

用python爬取豆瓣所有出版社https://read.douban.com/provider/all

data=urllib.request.urlopen(‘https://read.douban.com/provider/all’).read()

print(type(data))

<class ‘bytes’ >

對資料格式進行轉換

da=data.decode(‘utf-8’)

print(type(da))

<class ‘str’>

import re
import urllib.request

pat='<div class="name">(.*?)</div>' #正規表達式
data=urllib.request.urlopen('https://read.douban.com/provider/all').read()
da=data.decode('utf-8') #對爬取的網頁bytes格式轉化為str
rst=re.compile(pat).findall(str(da))
#寫入文本中
f=open('F:/pytest/unit/prod.txt','w')
for i in rst:
  f.write(i+'\n')
  #f.write('\n')
print(rst)
f.close()