Python爬虫之正则表达式（2）

# 最常规的匹配
import re
content = 'Hello 123 4567 World_This is a Regex Demo'
print(len(content))
result = re.match('^Hello\s\d\d\d\s\d{4}\s\w{10}.*Demo$', content)
print(result)
print(result.group())
print(result.span())

# 泛匹配
import re
content = 'Hello 123 4567 World_This is a Regex Demo'
print(len(content))
result = re.match('^Hello.*Demo$', content)
print(result)
print(result.group())
print(result.span())

# 匹配目标
import re
content = 'Hello 1234567 World_This is a Regex Demo'
print(len(content))
# # 注意匹配字符串里面带小括号的用法
result = re.match('^Hello\s(\d+)\sWorld.*Demo$', content)
print(result)
print(result.group(1))
print(result.span())

# 贪婪匹配
import re
content = 'Hello 1234567 World_This is a Regex Demo'
result = re.match('^He.*(\d+).*Demo$', content)
print(result)
print(result.group(1))

# 非贪婪匹配
import re
content = 'Hello 1234567 World_This is a Regex Demo'
# 多了一个问号变成了非贪婪匹配
result = re.match('^He.*?(\d+).*Demo$', content)
print(result)
print(result.group(1))

# 匹配模式
import re
content = '''Hello 1234567 World_This
is a Regex Demo
'''
# .可以匹配处了换行符以外的所有字符， 后面加上re.S就可以匹配任意字符了
result = re.match('^He.*?(\d+).*?Demo$', content, re.S)
print(result)
print(result.group(1))

# 特殊符号用\转义
import re
content = 'price is $5.00'
result = re.match('price is \$5\.00', content)
print(result)

# 尽量使用泛匹配、使用括号得到匹配目标、尽量使用非贪婪模式、有换行符就用re.S

# re.search
# re.search 扫描整个字符串并返回第一个成功的匹配
# re.match  是从字符串首字母开始匹配
import re
content = 'Extra strings Hello 1234567 World_This is a Regex Demo'
result = re.search('Hello.*?(\d+).*?Demo', content)
print(result)
print(result.group(1))

# 总结：为匹配方便，能用search就不用match