public IList <FeedEntity> GetList() { var list = new List <FeedEntity>(); for (int i = 1; i < 1000; i++) { web.URL = string.Format(url, i); string html = web.Get(); var mats = reg_title.Matches(html); if (mats.Count == 0) { break; } foreach (Match mat in mats) { var fd = new FeedEntity(); fd.Url = "http://blog.chinaunix.net" + mat.Groups[1].Value; fd.Title = mat.Groups[2].Value; if (fd.Title.StartsWith("[转载]")) { fd.Title = fd.Title.Substring(4); } list.Add(fd); } } return(list); }
public IList <FeedEntity> GetList() { var list = new List <FeedEntity>(); int p = 0; for (int i = 1; i < 1000; i++) { if (p > 0 && i > p) { break; } web.URL = string.Format(url, i); string html = web.Get(); if (p == 0) { var mp = Regex.Match(html, @"第(\d+)页"); if (mp.Success) { p = App.ToInt(mp.Groups[1].Value); } else { var mps = Regex.Matches(html, @">(\d+)</a><span class='pagesplit'>"); if (mps.Count > 0) { p = App.ToInt(mps[mps.Count - 1].Groups[1].Value); } else { p = 1; } } } var mats = reg_item.Matches(html); if (mats.Count == 0) { break; } foreach (Match mat in mats) { var m_t = reg_title.Match(mat.Value); var fd = new FeedEntity(); fd.Url = m_t.Groups[1].Value; fd.Title = m_t.Groups[2].Value; if (fd.Title == "本文被设定为主人好友可见") { continue; } list.Add(fd); } } return(list); }
public IList <FeedEntity> GetList() { var list = new List <FeedEntity>(); int p = 0; for (int i = 1; i < 1000; i++) { if (p > 0 && i > p) { break; } web.URL = string.Format(url, i); string html = web.Get(); if (p == 0) { var mp = Regex.Match(html, @"<a href=""/\?page=(\d+)""[^>]*>[^<]+?</a> <a href=""/\?page=2"" class=""next_page"""); if (mp.Success) { p = App.ToInt(mp.Groups[1].Value); } else { p = 1; } } var mats = reg_item.Matches(html); if (mats.Count == 0) { break; } foreach (Match mat in mats) { Match m_t = reg_title.Match(mat.Value); if (!m_t.Success) { continue; } var fd = new FeedEntity(); fd.Url = url.Split('?')[0] + m_t.Groups[1].Value.TrimStart('/'); fd.Title = m_t.Groups[2].Value; list.Add(fd); } System.Threading.Thread.Sleep(1000); } return(list); }
public IList <FeedEntity> GetList() { var list = new List <FeedEntity>(); int p = 0; for (int i = 1; i < 1000; i++) { if (p > 0 && i > p) { break; } web.URL = string.Format(url, i); string html = web.Get(); if (p == 0) { var mp = Regex.Match(html, @"共(\d+)页"); if (mp.Success) { p = App.ToInt(mp.Groups[1].Value); } else { p = 1; } } var mats = reg_title.Matches(html); if (mats.Count == 0) { break; } foreach (Match mat in mats) { var fd = new FeedEntity(); fd.Url = mat.Groups[1].Value; fd.Title = mat.Groups[2].Value; if (fd.Title.StartsWith("[转载]")) { fd.Title = fd.Title.Substring(4); } list.Add(fd); } } return(list); }
public IList <FeedEntity> GetList() { var list = new List <FeedEntity>(); int p = 0; for (int i = 1; i < 1000; i++) { if (p > 0 && i > p) { break; } web.URL = string.Format(url, i); string html = web.Get(); if (p == 0) { var mp = Regex.Match(html, @"页数 \( 1/(\d+) \)"); if (mp.Success) { p = App.ToInt(mp.Groups[1].Value); } else { p = 1; } } var mats = reg_title.Matches(html); if (mats.Count == 0) { break; } foreach (Match mat in mats) { var fd = new FeedEntity(); fd.Url = "http://" + url.Split('/')[2] + mat.Groups[2].Value; fd.Title = mat.Groups[3].Value; list.Add(fd); } } return(list); }
public IList <FeedEntity> GetList() { var list = new List <FeedEntity>(); for (int i = 1; i < 1000; i++) { web.URL = string.Format(url, i); string html = web.Get(); var mats = reg_title.Matches(html); if (mats.Count == 0) { break; } foreach (Match mat in mats) { var fd = new FeedEntity(); fd.Url = mat.Groups[1].Value; fd.Title = mat.Groups[2].Value; list.Add(fd); } } return(list); }
private string[] GetColumnUrls(string alias) { IList <string> urls = new List <string>(); string url = "http://blog.csdn.net/column/details/" + alias + ".html?page={0}"; int p = 0; WebUtility web = new WebUtility(); web.Encode = Encoding.UTF8; for (int i = 1; i < 100; i++) { if (p > 0 && i > p) { break; } web.URL = string.Format(url, i); string html = web.Get(); if (p == 0) { var mp = Regex.Match(html, @"共(\d+)页"); if (mp.Success) { p = App.ToInt(mp.Groups[1].Value); } else { p = 1; } } var mats = reg_title.Matches(html); if (mats.Count == 0) { break; } foreach (Match mat in mats) { urls.Add(mat.Groups[1].Value); } } string[] ss = new string[urls.Count]; for (int i = 0; i < urls.Count; i++) { ss[i] = urls[i]; } return(ss); }
public SinaService(string un) { url = "http://photo.blog.sina.com.cn/" + un; web = new WebUtility(); web.URL = url; string html = web.Get(); Match mat = Regex.Match(html, @"(?i)<a href=""(.+?)"">博文目录</a>"); if (mat.Success) { url = mat.Groups[1].Value.Replace("_1.html", "_{0}.html"); } else { throw new Exception("获取博客列表失败"); } }
public B51CtoService(string un) { url = "http://" + un + ".blog.51cto.com"; web = new WebUtility(); web.Encode = Encoding.GetEncoding("gb2312"); web.URL = url; string html = web.Get(); var m = Regex.Match(html, @"<a href=""/all/(.+?)"" class=""fr"">"); if (m.Success) { url += "/all/" + m.Groups[1].Value + "/page/{0}"; } else { throw new Exception("获取博客列表失败"); } }
public SohuService(string un) { url = "http://" + un + ".blog.sohu.com/entry/"; web = new WebUtility(); web.URL = url; web.Encode = Encoding.GetEncoding("gbk"); string html = web.Get(); Match mat = Regex.Match(html, @"var _ebi = '(.+?)';"); if (mat.Success) { url = "http://" + un + ".blog.sohu.com/action/v_frag-ebi_" + mat.Groups[1].Value + "-pg_{0}/entry/"; } else { throw new Exception("获取博客列表失败"); } }
public B163Service(string un) { url = "http://blog.163.com/" + un + "/blog/"; web = new WebUtility(); web.URL = url; string html = web.Get(); var mat = Regex.Match(html, @"userId:(\d+)"); if (mat.Success) { userId = mat.Groups[1].Value; } else { throw new Exception("获取博客列表失败"); } url = "http://api.blog.163.com/" + un + "/dwr/call/plaincall/BlogBeanNew.getBlogs.dwr"; }
public FeedEntity GetEntity(string url) { var entity = new FeedEntity(); web.URL = url; string html = web.Get(); Match mat = reg_title2.Match(html); if (mat.Success) { entity.Title = mat.Groups[1].Value.Trim(); } mat = reg_con2.Match(html); if (mat.Success) { entity.Content = mat.Groups[1].Value.Trim(); } return(entity); }
private string[] GetColumnUrls(string alias) { IList<string> urls = new List<string>(); string url = "http://blog.csdn.net/column/details/" + alias + ".html?page={0}"; int p = 0; WebUtility web = new WebUtility(); web.Encode = Encoding.UTF8; for (int i = 1; i < 100; i++) { if (p > 0 && i > p) break; web.URL = string.Format(url, i); string html = web.Get(); if (p == 0) { var mp = Regex.Match(html, @"共(\d+)页"); if (mp.Success) p = App.ToInt(mp.Groups[1].Value); else p = 1; } var mats = reg_title.Matches(html); if (mats.Count == 0) break; foreach (Match mat in mats) { urls.Add(mat.Groups[1].Value); } } string[] ss = new string[urls.Count]; for (int i = 0; i < urls.Count; i++) { ss[i] = urls[i]; } return ss; }
public IList <FeedEntity> GetList() { var list = new List <FeedEntity>(); int p = 0; for (int i = 1; i < 1000; i++) { if (p > 0 && i > p) { break; } web.URL = string.Format(url, i); string html = web.Get(); if (p == 0) { var mp = Regex.Match(html, @"共(\d+)页"); if (mp.Success) { p = App.ToInt(mp.Groups[1].Value); } else { p = 1; } } var mats = reg_title.Matches(html); if (mats.Count == 0) { break; } foreach (Match mat in mats) { var fd = new FeedEntity(); fd.Url = mat.Groups[1].Value.Split('#')[0].Split('?')[0].ToLower(); fd.Title = mat.Groups[3].Value; if (fd.Url.Split('/')[3] != url.Split('/')[3]) { continue; } if (fd.Title.StartsWith("[转]")) { fd.Title = fd.Title.Substring(3); } bool has = false; foreach (var fe in list) { if (fe.Url == fd.Url || fe.Title == fd.Title) { has = true; break; } } if (has) { continue; } list.Add(fd); } } return(list); }