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))
对数据格式进行转换
da=data.decode(‘utf-8’)
print(type(da))
import re
import urllib.request
pat='(.*?)' #正则表达式
data=urllib.request.urlopen('https://read.douban.com/provider/all').read()
da=data.decode('utf-8') #对爬取的网页bytes格式转化为str
rst=re.compile(pat).findall(str(da))
#写入文本中
f=open('F:/pytest/unit/prod.txt','w')
for i in rst:
f.write(i+'\n')
#f.write('\n')
print(rst)
f.close()