python爬虫篇之正则表达式(四)

INFO: System startedERROR: Could not connect to databaseWARNING: Low disk spaceERROR: File not found

import rewith open(r"mypackage\log1.log") as f:    logs_text = f.read()print("logs_text:::", repr(logs_text))# (1)查询所有ERRORret = re.findall("ERROR:.*", logs_text)print(ret)print("下面是search输出结果")print("------------------------")# (2)查询第一个ERROR# 匹配成功，返回的是一个match对象，否则，返回一个Noneret1 = re.search("ERROR:.*", logs_text)print(ret1)print(ret1.span())print(ret1.start())print(ret1.end())print(ret1.group())

import retext = """服务器的IP地址如下：主服务器：192.168.1.1备用服务器：10.0.0.5外部服务器：172.16.254.1无效IP：256.100.50.25和192.168.1.256"""# 匹配所有ipret = re.findall(r"\b(?:\d{1,3}\.){3}\d{1,3}\b",text)print(f"用findall匹配所有ip：{ret}")ret = re.search(r"\b(?:\d{1,3}\.){3}\d{1,3}\b",text)print(ret)print("用search匹配首个符合的ip", ret.group())# 有名分组# 匹配第一个外部服务器IP地址print("search指定一个ip")print("-------------------------")ret2 = re.search(r"外部服务器：\b(?P<outer_ip>(?:\d{1,3}\.){3}\d{1,3})\b", text)print(ret2)print(ret2.group())print(ret2.group("outer_ip"))

import retext = """服务器的IP地址如下：主服务器：192.168.1.1备用服务器：10.0.0.5外部服务器：172.16.254.1无效IP：256.100.50.25和192.168.1.256"""ret1 = re.search(r"^外部服务器：\b(?P<outer_ip>(?:\d{1,3}\.){3}\d{1,3})\b", text)print(ret1)# match的效果相当于search前面加了个^ret2 = re.search(r"外部服务器：\b(?P<outer_ip>(?:\d{1,3}\.){3}\d{1,3})\b", text)print(ret2)print(ret2.group())print(ret2.group("outer_ip"))

import res = "yuan,rain,eric"print(s.split(","))s = "yuan rain   eric    alvin"ret = re.split(r"\s+", s)print(ret)

import re# sub将多个字符替换成一个，下面是多个空格替换成单空格txt = "my name    is    ooaac"ret = re.sub(r"\s+", repl=" ", string=txt)print(ret)

import res = "15100649928,123@qq.com,+8613653287791,666@163.com"ret = re.findall(r"(?:\+86)?1[3-9]\d{9}",s)print(f"用findall筛选出的结果：{ret}")s1 = "15100649928,123@qq.com,+8613653287791,666@163.com"s2 = "15144449928,123@qq.com,+8613222228791,666@163.com 13622227791"s3 = "15100655928,123@qq.com,+8613677787791,666@163.com"reg_compile = re.compile(r"(?:\+86)?1[3-9]\d{9}")ret1 = reg_compile.findall(s1)print(ret1)ret2 = reg_compile.findall(s2)print(ret2)ret3 = reg_compile.findall(s3)print(ret3)