Python爬虫之正则表达式（3）

# re.sub
# 替换字符串中每一个匹配的子串后返回替换后的字符串
import re
content = 'Extra strings Hello 1234567 World_This is a Regex Demo Extra strings'
content = re.sub('d+', '', content)
print(content)

import re
content = 'Extra strings Hello 1234567 World_This is a Regex Demo Extra strings'
content = re.sub('d+', 'Replacement', content)
print(content)

# 1 是转义字符
import re
content = 'Extra strings Hello 1234567 World_This is a Regex Demo Extra strings'
content = re.sub('(d+)', r'1 8910', content)
print(content)

# re.compile
# 将正则字符串编译成正则表达式对象
# 将一个正则表达式串编译成正则对象，以便于复用该匹配模式
import re
content = '''Hello 1234567 World_This
is a Regex Demo'''
pattern = re.compile('Hello.*Demo', re.S)
result = re.match(pattern, content)
print(result)

下面是爬取豆瓣图书的实战代码

import requests
import re
content = requests.get('https://book.douban.com/').text
# print(content)
pattern = re.compile('<li.*?cover.*?title="(.*?)".*?author">(.*?)</div>.*?year">(.*?)</span>.*?</li>', re.S)
results = re.findall(pattern, content)
for result in results:
    name, author, date = result
    author = re.sub("s", "", author)
    date = re.sub("s", "", date)
    print("【书名】：", name, " 【作者】：", author, " 【出版年】：", date)

本篇内容为：崔庆才爬虫学习笔记