Data collection program

The data collection program collects information about talents in a talent network. For the first time, you can write a blog.

// Create a data table based on the following fields

Reference content is as follows: Public partial class form2: Form { Public form2 () { Initializecomponent (); } // Name Public static string XM = ""; // Age Public static string NL = ""; // Gender Public static string XB = ""; // Height Public static string SG = ""; // Political outlook Public static string Mm = ""; // Nationality Public static string MZ = ""; // Education level Public static string XL = ""; // Marital status Public static string HK = ""; // Major Public static string ZY = ""; // Work experience Public static string gzjy = ""; // Employer Public static string zzdw = ""; // Position Public static string zzzw = ""; // Work experience Public static string gzjl = ""; // Requires monthly salary Public static string YX = ""; // Working nature Public static string gzxz = ""; // Intention to apply for a job Public static string qzyx = ""; // Specific position Public static string jtzw = ""; // Expected Place of Work Public static string qwgzd = ""; // Education, language level, technical expertise Public static string Qt = ""; Private void button#click (Object sender, eventargs E) { Label1.text = "collecting data ...... "; // Traverse the data page For (INT I = 1; I <= 50; I ++) { CJ ("http://www.xcjob.cn/renli.asp? Pageno = "+ I ); } Label1.text = "Congratulations! collection is complete! "; MessageBox. Show ("Congratulations! collection is complete! "); } // Collect data Private void CJ (string URL) { // Obtain the page source file (HTML) String strwebcontent = ym (URL ); // Extract the data-related source code based on the tags in the HTML. Int ibodystart = strwebcontent. indexof ("<body", 0 ); Int AAA = strwebcontent. indexof ("Keyword:", ibodystart ); Int itablestart = strwebcontent. indexof ("<Table", AAA ); Int itableend = strwebcontent. indexof ("</table>", itablestart ); String strweb = strwebcontent. substring (itablestart, itableend-itablestart ); // Generate htmldocument Htmlelementcollection htmltr = htmltr_content (strweb, "TR "); Foreach (htmlelement TR in htmltr) { Try { // Name XM = tr. getelementsbytagname ("A") [0]. innertext; // Obtain the URL of the detailed information page String A = tr. getelementsbytagname ("A") [0]. getattribute ("href"). tostring (); A = "http://www.xcjob.cn" + A. substring (11 ); Content (); } Catch {} } } // Collect detailed data Private void content (string URL) { Try { String strwebcontent = ym (URL ); // Extract the data-related source code based on the tags in the HTML. Int ibodystart = strwebcontent. indexof ("<body", 0 ); Int itablestart = strwebcontent. indexof ("browsing Times", ibodystart ); Int itableend = strwebcontent. indexof ("<Table", itablestart ); Int dd = strwebcontent. indexof ("</table>", itableend ); String strweb = strwebcontent. substring (itableend, DD-itableend + 8 ); Htmlelementcollection htmltr = htmltr_content (strweb, "table "); Foreach (htmlelement TR in htmltr) { Try { // Age NL = tr. getelementsbytagname ("TR") [1]. getelementsbytagname ("TD") [1]. innertext; // Gender String xb_sg = tr. getelementsbytagname ("TR") [1]. getelementsbytagname ("TD") [3]. innertext; XB = xb_sg.substring (0, 1 ); // Height SG = xb_sg.substring (11 ); // Political outlook Mm = tr. getelementsbytagname ("TR") [2]. getelementsbytagname ("TD") [1]. innertext; // Nationality MZ = tr. getelementsbytagname ("TR") [2]. getelementsbytagname ("TD") [3]. innertext; // Education level XL = tr. getelementsbytagname ("TR") [3]. getelementsbytagname ("TD") [1]. innertext; // Marital status HK = tr. getelementsbytagname ("TR") [3]. getelementsbytagname ("TD") [3]. innertext; // Major ZY = tr. getelementsbytagname ("TR") [5]. getelementsbytagname ("TD") [1]. innertext; // Work experience Gzjy = tr. getelementsbytagname ("TR") [5]. getelementsbytagname ("TD") [3]. innertext; // Employer Zzdw = tr. getelementsbytagname ("TR") [6]. getelementsbytagname ("TD") [1]. innertext; // Position Zzzw = tr. getelementsbytagname ("TR") [6]. getelementsbytagname ("TD") [3]. innertext; // Work experience Gzjy = tr. getelementsbytagname ("TR") [7]. getelementsbytagname ("TD") [1]. innertext; // Requires monthly salary YX = tr. getelementsbytagname ("TR") [9]. getelementsbytagname ("TD") [1]. innertext; // Working nature Gzxz = tr. getelementsbytagname ("TR") [9]. getelementsbytagname ("TD") [3]. innertext; // Intention to apply for a job Qzyx = tr. getelementsbytagname ("TR") [10]. getelementsbytagname ("TD") [1]. innertext; // Specific position Jtzw = tr. getelementsbytagname ("TR") [10]. getelementsbytagname ("TD") [3]. innertext; // Expected Place of Work Qwgzd = tr. getelementsbytagname ("TR") [11]. getelementsbytagname ("TD") [1]. innertext; // Education, language level, technical expertise Qt = tr. getelementsbytagname ("TR") [13]. getelementsbytagname ("TD") [1]. innertext; Insert (); } Catch {} } } Catch {} } // Insert data into the database Private void insert () { Try { String STR = "provider = Microsoft. Jet. oledb.4.0; Data Source = data. mdb "; String SQL = "insert into talent information (name, age, gender, height, political outlook, ethnicity, education, marital status, Major ,"; SQL + = "work experience, in-service organization, in-service position, work experience, requirements for monthly salary, job nature, job intention, specific job title, desired job location, other) values "; SQL + = "('" + XM + "'," + NL + ", '" + XB + "', '" + SG + "', '"+ mm +"', '"+ MZ +"', '"+ XL +"', '"+ HK +"', '"+ ZY + "', '"+ gzjy +"', '"+ zzdw +"', '"+ zzzw + "',"; SQL + = "'" + gzjy + "', '" + Yx + "', '" + gzxz + "', '" + qzyx + "', '"+ jtzw +"', '"+ qwgzd +"', '"+ QT + "')"; Oledbconnection con = new oledbconnection (STR ); Oledbcommand COM = new oledbcommand (SQL, con ); Con. open (); Com. executenonquery (); Con. Close (); } Catch {} } // Return an htmlelementcollection and query the content. Private htmlelementcollection htmltr_content (string strweb, string TJ) { Try { // Generate htmldocument Webbrowser Webb = new webbrowser (); Webb. navigate ("about: blank "); // Window.doc ument returns an htmldocument object, indicating operations on an HTML document // The htmldocument object is created on the basis of xmldocument and has all the method attributes of xmldocument Htmldocument htmldoc = Webb. Document. opennew (true ); Htmldoc. Write (strweb ); Htmlelementcollection htmltr = htmldoc. getelementsbytagname (TJ ); Return htmltr; } Catch {return NULL ;} } // Obtain the original URL code Private string ym (string URL) { String strresult = ""; Try { Httpwebrequest request = (httpwebrequest) webrequest. Create (URL ); Request. method = "get "; Httpwebresponse response = (httpwebresponse) request. getresponse (); Stream streamreceive = response. getresponsestream (); Encoding encoding = encoding. getencoding ("gb2312 "); Streamreader = new streamreader (streamreceive, encoding ); Strresult = streamreader. readtoend (); } Catch {} Return strresult; } }

// This program is not very well written. It is all traversed through the for loop, and the efficiency is not too high. The expert can use multiple threads to give pointers.