//读取
public List <PracticeInfo> getPracticeInfoFromFile(string file)
{
StreamReader sr = new StreamReader(file, Encoding.UTF8);
String data = sr.ReadToEnd();
//用于存储读取的每一行数据
List <String> li = new List <String>();
List <PracticeInfo> list = new List <PracticeInfo>();
//按行切分，存入li
string[] m = data.Split(new char[] { '\n' });
for (int k = 0; k < m.Length; k++)
{
li.Add(m[k]);
}
sr.Close();
//每行切分，存入具体的pracinfo
for (int i = 0; i < li.Count - 1; i++)
{
PracticeInfo tempPrac = new PracticeInfo();
string tempLi = li[i];
string[] n = tempLi.Split(new char[] { '\t' });
SetPracticeInfoByString(tempPrac, n);
list.Add(tempPrac);
}
return(list);
}
public void SetPracticeInfoByString(PracticeInfo prf, String[] contentlist)
{
prf.name = contentlist[0];
prf.request = contentlist[1];
prf.duty = contentlist[2];
prf.location = contentlist[3];
prf.compname = contentlist[4];
prf.compinfo = contentlist[5];
prf.compweb = contentlist[6];
}
/// <summary>
/// return List<practiceInfo>to store all information
/// </summary>
/// <param name="ID"></param>
/// <param name="ComID"></param>
/// <returns></returns>
public List <PracticeInfo> getPracticeInfo(List <int> ID, List <int> ComID)
{
List <PracticeInfo> practiceInfo = new List <PracticeInfo>();
for (int i = 0; i < ID.Count; i++)
{
PracticeInfo tempInfo = new PracticeInfo();
string url = "https://www.nowcoder.com/recommend-intern/" + ComID[i] + "?jobId=" + ID[i];
string content = GetContent(url);
//清楚html占位符
content = content.Replace(" ", " ");
//获取岗位名称
content = content.Substring(content.IndexOf("rec-job") + 14);
tempInfo.name = Insurance(content.Substring(0, content.IndexOf("<")));
//获取岗位职责
content = content.Substring(content.IndexOf("岗位职责"));
string dutycontent = content.Substring(0, content.IndexOf("</dl>") + 5);
//清除换行符对正则的影响
dutycontent = dutycontent.Replace("\n", "");
//清楚制表符对输出时切分的影响
dutycontent = dutycontent.Replace("\t", "");
//正则提取>和<之间的内容
Regex re = new Regex("(?<=>).*?(?=<)", RegexOptions.None);
MatchCollection mc1 = re.Matches(dutycontent);
string dutycontentr = "";
foreach (Match found in mc1)
{
dutycontentr += found;
}
tempInfo.duty = Insurance(dutycontentr);
//获取岗位要求
content = content.Substring(content.IndexOf("岗位要求"));
string reqcontent = content.Substring(0, content.IndexOf("</dl>") + 6);
//清除换行符对正则的影响
reqcontent = reqcontent.Replace("\n", "");
//清楚制表符对输出时切分的影响
reqcontent = reqcontent.Replace("\t", "");
MatchCollection mc2 = re.Matches(reqcontent);
string reqcontentr = "";
foreach (Match found in mc2)
{
reqcontentr += found;
}
tempInfo.request = Insurance(reqcontentr);
//获取公司名称
content = content.Substring(content.IndexOf("teacher-name") + 14);
tempInfo.compname = Insurance(content.Substring(0, content.IndexOf("<")));
//获取地址
content = content.Substring(content.IndexOf("com-lbs") + 9);
tempInfo.location = Insurance(content.Substring(0, content.IndexOf("<")));
//获取公司简介
content = content.Substring(content.IndexOf("com-detail") - 12);
string detailcontent = content.Substring(0, content.IndexOf("</p>") + 4);
//清除换行符对正则的影响
detailcontent = detailcontent.Replace("\n", "");
//清楚制表符对输出时切分的影响
detailcontent = detailcontent.Replace("\t", "");
MatchCollection mc3 = re.Matches(detailcontent);
string detailcontentr = "";
foreach (Match found in mc3)
{
detailcontentr += found;
}
tempInfo.compinfo = Insurance(detailcontentr);
//获取公司网址
content = content.Substring(content.IndexOf("http"));
tempInfo.compweb = Insurance(content.Substring(0, content.IndexOf("\"")));
practiceInfo.Add(tempInfo);
}
return(practiceInfo);
}
