【发布时间】:2012-03-14 23:04:53
【问题描述】:
我为自己编写了一个个人网络抓取工具,用于抓取艺术家信息。代码有效,但是当我按下按钮并开始处理 while 循环时,GUI 冻结。我得到了.refresh() 的文本框。但是我不能移动表格,取消程序的唯一方法是强制退出。我正在重写这个,所以我没有遇到这个问题。另外,我听说过踩踏,想看看这是否可行,并让它更快一点。该程序正在抓取 15,000 多个页面,然后每个页面还有另外 10 个左右的页面需要抓取。因此,该程序可能会运行几个小时才能最终完成。
这是我的代码。
private void btnGet_Click(object sender, EventArgs e)
{
int i = 0;
int maxCount = 15000; //11234 was last value
progressBar.Maximum = maxCount;
while (i <= maxCount)
{
txbURL.Text = "http://www.newreleasetuesday.com/albumdetail.php?album_id=" + i;
label.Text = i.ToString() + " out of " + maxCount.ToString() + " Done.";
progressBar.Value = i;
string url = txbURL.Text;
string sourceCode = sourceCode = WorkerClass.getSourceCode(url);
int startIndex = sourceCode.IndexOf("//alert(document.getElementById(\"remcheck\").value)");
sourceCode = sourceCode.Substring(startIndex, sourceCode.Length - startIndex);
//Start Artist Name
//Gets the Artist's ID
int idCountIndex = sourceCode.IndexOf(" by <a href=\"artistdetail.php?artist_id=") + 41;
int idCountEndIndex = sourceCode.IndexOf("\">", idCountIndex);
string artistID = sourceCode.Substring(idCountIndex, idCountEndIndex - idCountIndex) + "";
txbArtistID.Text = artistID;
//Gets Artist's Name
startIndex = sourceCode.IndexOf(" by <a href=\"artistdetail.php?artist_id=") + 43 + artistID.Length;
int endIndex = sourceCode.IndexOf("</a> | Genre", startIndex);
string artistName = sourceCode.Substring(startIndex, endIndex - startIndex) + "";
txbArtist.Text = artistName;
//End Artist Name
//Start Album Name
//Gets Album's ID
string albumID = url.Substring(url.IndexOf("=") + 1);
txbAlbumID.Text = albumID;
//Gets Album's Name
startIndex = sourceCode.IndexOf("absbottom\"></span></strong> ") + 28;
endIndex = sourceCode.IndexOf("</span></td>", startIndex);
string AlbumName = sourceCode.Substring(startIndex, endIndex - startIndex) + "";
txbAlbum.Text = AlbumName;
//End Album Name
//Start Genre
startIndex = sourceCode.IndexOf("</a> | Genre: ") + 14;
endIndex = sourceCode.IndexOf(" | ", startIndex);
string genre = sourceCode.Substring(startIndex, endIndex - startIndex) + "";
txbGenre.Text = genre;
//End Genre
//Start Release Date
startIndex = sourceCode.IndexOf("<a href=\"releasedate.php?release_date=") + 50;
endIndex = sourceCode.IndexOf(" </a></td>", startIndex);
string releaseDate = sourceCode.Substring(startIndex, endIndex - startIndex) + "";
txbReleaseDate.Text = releaseDate;
//End Release Date
//Start Pic URL
startIndex = sourceCode.IndexOf("<img src=\"") + 11;
endIndex = sourceCode.IndexOf("\" alt=", startIndex);
string PicURL = sourceCode.Substring(startIndex, endIndex - startIndex) + "";
PicURL = PicURL.Replace("amp;", "");
string fullLink = "http://www.newreleasetuesday.com/" + PicURL;
txbPicURL.Text = fullLink;
//End Pic URL
//Refresh UI (Updates textBoxes, labels, and progressBar with new values)
txbURL.Refresh();
txbArtist.Refresh();
txbAlbum.Refresh();
txbReleaseDate.Refresh();
txbGenre.Refresh();
txbPicURL.Refresh();
txbArtistID.Refresh();
txbAlbumID.Refresh();
label.Refresh();
progressBar.Refresh();
if (artistName == "")
{
// Adding info to Database if there is no artist name
string cs = "SERVER=asdf.net;" +
"DATABASE=music;" +
"UID=root;" +
"PASSWORD=asdf;";
MySqlConnection conn = null;
conn = new MySqlConnection(cs);
conn.Open();
MySqlCommand cmd = new MySqlCommand();
cmd.Connection = conn;
cmd.CommandText = "INSERT INTO `emptyalbums` (id, albumid) VALUES('',@albumid)";
cmd.Prepare();
cmd.Parameters.AddWithValue("@albumid", albumID);
cmd.ExecuteNonQuery();
conn.Close();
}
else
{
// Adding info to Database if there is an artist name
string cs = "SERVER=asdf.net;" +
"DATABASE=music;" +
"UID=root;" +
"PASSWORD=asdf;";
MySqlConnection conn = null;
conn = new MySqlConnection(cs);
conn.Open();
MySqlCommand cmd = new MySqlCommand();
cmd.Connection = conn;
cmd.CommandText = "INSERT INTO `database` (id, artist, album, releasedate, genre, pictureurl, artistid, albumid) VALUES('',@artist, @album, @releasedate, @genre, @pictureurl, @artistid, @albumid)";
cmd.Prepare();
cmd.Parameters.AddWithValue("@artist", artistName);
cmd.Parameters.AddWithValue("@album", AlbumName);
cmd.Parameters.AddWithValue("@releasedate", releaseDate);
cmd.Parameters.AddWithValue("@genre", genre);
cmd.Parameters.AddWithValue("@pictureurl", fullLink);
cmd.Parameters.AddWithValue("@artistid", artistID);
cmd.Parameters.AddWithValue("@albumid", albumID);
cmd.ExecuteNonQuery();
conn.Close();
}
i++;
}
任何信息都会有很长的路要走。 谢谢, 索隆
【问题讨论】:
标签: c# winforms web-scraping