实战之使用正则表达式截取热点数据,并封装成以某个热点为单位的dictionary中,最终构成list<dictionary>

首先,不错的正则表达式学习基础

正则表达式30分钟入门教程

切入正题:

HTTP

响应output为

"<?xml version=\"1.0\" encoding=\"UTF-8\" ?>\n<root>\n  <responseHeader>\n    <sequence>1364044260890</sequence>\n    <timestamp>2013-03-23 21:10:18</timestamp>\n    <version>1.0.0</version>\n    <returnCode>0</returnCode>\n    <errorMessage>成功</errorMessage>\n  </responseHeader>\n  <responsePage>\n    <hasNextPage>true</hasNextPage>\n    <hasPreviousPage>false</hasPreviousPage>\n    <lastPageNumber>4</lastPageNumber>\n    <totalCount>62</totalCount>\n    <thisPageFirstElementNumber>1</thisPageFirstElementNumber>\n    <thisPageLastElementNumber>20</thisPageLastElementNumber>\n    <nextPageNumber>2</nextPageNumber>\n    <previousPageNumber>0</previousPageNumber>\n    <pageSize>20</pageSize>\n    <thisPageNumber>1</thisPageNumber>\n    <firstResult>0</firstResult>\n  </responsePage>\n  <hotpointInfoList>\n    <hotpointInfo>\n      <name>天朗明居北区C N5栋</name>\n      <nasid>301693</nasid>\n      <address>广州市天河区中山大道与车陂路交汇处</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3862</longitude>\n      <latitude>23.1296</latitude>\n      <coverageArea>本次工程覆盖N5栋楼高26层。</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>393.5081511793397</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>棠下街道办事处</name>\n      <nasid>302082</nasid>\n      <address>棠下棠德东路棠德小区E栋-1棠下街道办事处</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3815</longitude>\n      <latitude>23.1354</latitude>\n      <coverageArea>棠下街道办事处1-2F</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>402.49152162918364</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>天朗明居南区C S1</name>\n      <nasid>301690</nasid>\n      <address>广州市天可区中山大道与车陂路交汇处</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3862</longitude>\n      <latitude>23.1284</latitude>\n      <coverageArea>S1栋</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>499.4094297245712</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>正果工商所</name>\n      <nasid>301470</nasid>\n      <address>增城区正果大道88号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3886</longitude>\n      <latitude>23.1311</latitude>\n      <coverageArea>工商所办公大厅、2F</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>523.7109776951346</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>易初莲花车陂店C</name>\n      <nasid>301864</nasid>\n      <address>广州市天河区车陂路</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3854</longitude>\n      <latitude>23.1258</latitude>\n      <coverageArea>卖场区域</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>748.1531798245414</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景东御苑C8SW08</name>\n      <nasid>301891</nasid>\n      <address>广州市天河区中山大道190号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3839</longitude>\n      <latitude>23.1256</latitude>\n      <coverageArea>G1-G6,H1-H2全部楼层公共区域</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>749.2729513269494</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景东御苑C7SW07</name>\n      <nasid>301892</nasid>\n      <address>广州市天河区中山大道190号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3839</longitude>\n      <latitude>23.1256</latitude>\n      <coverageArea>G1-G6,H1-H2全部楼层公共区域</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>749.2729513269494</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景东御苑C4SW04</name>\n      <nasid>301894</nasid>\n      <address>广州市天河区中山大道190号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3839</longitude>\n      <latitude>23.1255</latitude>\n      <coverageArea>G1-G6,H1-H2全部楼层公共区域</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>760.1215323422311</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景东御苑C3SW03</name>\n      <nasid>301895</nasid>\n      <address>广州市天河区中山大道190号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3839</longitude>\n      <latitude>23.1255</latitude>\n      <coverageArea>G1-G6,H1-H2全部楼层公共区域</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>760.1215323422311</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景东御苑C2SW02</name>\n      <nasid>301896</nasid>\n      <address>广州市天河区中山大道190号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3839</longitude>\n      <latitude>23.1255</latitude>\n      <coverageArea>G1-G6,H1-H2全部楼层公共区域</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>760.1215323422311</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景东御苑C5SW05</name>\n      <nasid>301893</nasid>\n      <address>广州市天河区中山大道190号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3839</longitude>\n      <latitude>23.1256</latitude>\n      <coverageArea>G1-G6,H1-H2全部楼层公共区域</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>760.1215323422311</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景东御苑C6SW06</name>\n      <nasid>301890</nasid>\n      <address>广州市天河区中山大道190号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3839</longitude>\n      <latitude>23.1256</latitude>\n      <coverageArea>G1-G6,H1-H2全部楼层公共区域</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>760.3864516706291</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景东御苑G3栋</name>\n      <nasid>301898</nasid>\n      <address>广州市天河区中山大道192号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3838</longitude>\n      <latitude>23.1254</latitude>\n      <coverageArea>1F-28F</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>771.2390231563601</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>南洋冠盛酒店</name>\n      <nasid>302093</nasid>\n      <address>天府路11号</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3805</longitude>\n      <latitude>23.1258</latitude>\n      <coverageArea>酒店1-13F</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>805.295261820077</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景花园南苑东区B骏灏轩D栋SW10</name>\n      <nasid>301910</nasid>\n      <address>广州市天河区中山大道旁骏景花园</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3819</longitude>\n      <latitude>23.1239</latitude>\n      <coverageArea>骏灏轩D栋</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>967.8317796098889</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景花园南苑东区B骏盈轩D栋SW15</name>\n      <nasid>302068</nasid>\n      <address>广州市天河区中山大道旁骏景花园</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3817</longitude>\n      <latitude>23.1239</latitude>\n      <coverageArea>骏盈轩D栋</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>969.8902627929679</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景花园南苑东区B骏盈轩B栋SW16</name>\n      <nasid>302067</nasid>\n      <address>广州市天河区中山大道旁骏景花园</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3818</longitude>\n      <latitude>23.1239</latitude>\n      <coverageArea>骏盈轩B栋</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>969.8902627929679</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景花园南苑东区B骏盈轩E栋SW14</name>\n      <nasid>302069</nasid>\n      <address>广州市天河区中山大道旁骏景花园</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3817</longitude>\n      <latitude>23.1238</latitude>\n      <coverageArea>骏盈轩E栋</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>969.8902627929679</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景花园南苑东区B骏灏轩F栋SW12</name>\n      <nasid>302071</nasid>\n      <address>广州市天河区中山大道旁骏景花园</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3817</longitude>\n      <latitude>23.1238</latitude>\n      <coverageArea>骏灏轩F栋</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>969.8902627929679</distance>\n    </hotpointInfo>\n    <hotpointInfo>\n      <name>骏景花园南苑东区B骏灏轩E栋SW11</name>\n      <nasid>302072</nasid>\n      <address>广州市天河区中山大道旁骏景花园</address>\n      <province>200</province>\n      <cityCode>440100</cityCode>\n      <type>99</type>\n      <longitude>113.3817</longitude>\n      <latitude>23.1238</latitude>\n      <coverageArea>骏灏轩E栋</coverageArea>\n      <isRecommend>0</isRecommend>\n      <distance>969.8902627929679</distance>\n    </hotpointInfo>\n  </hotpointInfoList>\n</root>"

需要截取每个

hotpointInfo中的address,name,distance等信息

利用正则表达式

代码如下:

                        MatchCollection hotspotMatches = Regex.Matches(output, "<hotpointInfo>.*?<name>(?<name>.*?)</name>.*?<address>(?<address>.*?)</address>.*?<cityCode>(?<city>.*?)</cityCode>.*?<type>(?<hottype>.*?)</type>.*?<longitude>(?<longitude>.*?)</longitude>.*?<latitude>(?<latitude>.*?)</latitude>.*?(.*?<coverageArea>(?<coverarea>.*?)</coverageArea>)?.*?<distance>(?<distance>.*?)</distance>.*?</hotpointInfo>", RegexOptions.Singleline);
                        foreach (Match hotspotMatch in hotspotMatches)
                        {
                            Dictionary<String, String> dict = new Dictionary<string, string>();
                            double distanceDou = double.Parse(hotspotMatch.Groups["distance"].Value);
                            //make display 110 meter 
                            //not 110.12232453242 meter
                            int distanceInt = (int)distanceDou;
                            dict.Add("name", hotspotMatch.Groups["name"].Value);
                            dict.Add("address", hotspotMatch.Groups["address"].Value);
                            string city = FromCityIdToName(hotspotMatch.Groups["city"].Value);
                            dict.Add("city", city);
                            dict.Add("hottype", hotspotMatch.Groups["hottype"].Value);
                            dict.Add("longitude", hotspotMatch.Groups["longitude"].Value);
                            dict.Add("latitude", hotspotMatch.Groups["latitude"].Value);
                            dict.Add("coverarea", hotspotMatch.Groups["coverarea"].Value);
                            dict.Add("distance", Convert.ToString(distanceInt));
                            dict.Add("total", totalPage);
                            ((List<Dictionary<String, String>>)returnData).Add(dict);
                        }


原文地址:https://www.cnblogs.com/fifa0329/p/4536680.html