Python中的正则表达式找到所有符合要求的字符串

雨点打透心脏的1/2处 2022-10-18 01:41 167阅读 0赞

正则匹配中文，固定形式：**\\u4E00-\\u9FA5**

re.findall("正则表达式","处理的内容",re.DOTALL)

import re
    from lxml import etree
    
    def demo():
        content = """<?xml version="1.0" encoding="GB2312"?>
            <tree>
            <tree curCode="110000" text="北京局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="120000" text="天津局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="130000" text="河北局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="140000" text="山西局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="150000" text="内蒙古局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="210000" text="辽宁局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="220000" text="吉林局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="230000" text="黑龙江局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="310000" text="上海局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="320000" text="江苏局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="330000" text="浙江局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="340000" text="安徽局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="350000" text="福建局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="360000" text="江西局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="370000" text="山东局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="380000" text="宁波局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="390000" text="厦门局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="410000" text="河南局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="420000" text="湖北局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="430000" text="湖南局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="440000" text="广东局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="450000" text="广西局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="460000" text="海南局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="470000" text="深圳局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="480000" text="珠海局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="500000" text="重庆局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="510000" text="四川局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="520000" text="贵州局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="530000" text="云南局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="540000" text="西藏局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="610000" text="陕西局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="620000" text="甘肃局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="630000" text="青海局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="640000" text="宁夏局本部" attrsName="" attrs="" attrSplit="@#$" />
            <tree curCode="650000" text="新疆局本部" attrsName="" attrs="" attrSplit="@#$" />
            </tree>"""
        #Re = re.findall(r'([0-9]{6})\S.*?text=\S(.*?局本部)\S', S, re.DOTALL)
        Re = re.findall(r'([0-9]{6})\S.*?text=\S([\u4E00-\u9FA5]+)\S', content, re.DOTALL)
        if Re:
            # print(Re)
            i = 1
            # for 循环内部使用变量 in 列表
            for name in Re:
                print("QualityInspectionBureau" + str(i) + "(\"" + name[0] + "\",\"" + name[1] + "\")")
                i = i + 1
    
    demo()

正则表达式分析：(\[0-9\]\{6\})\\S.\*?text=\\S(\[\\u4E00-\\u9FA5\]+)\\S

第一段：(\[0-9\]\{6\})表示**6位数字组合**

第二段：\\S.\*?text=\\S 表示**" text="组合**

第三段：\\S(\[\\u4E00-\\u9FA5\]+)\\S 表示**"中文文字组合"**