//单线程，单个网页爬取
public static bool StartCrawl(Project project /*, CrawlerService crawler*/)
{
CrawlStart();
//存储网页url
List <string> urls = new List <string>();
//存储图片ul
List <string> imgUrls = new List <string>();
///初始化爬虫
InitCrawl(project);
//如果是贴吧网址则使用爬取贴吧图片的策略
if (TiebaHTMLService.isTiebaSite(project.ImgInputData.Url))
{
TibaCrawl(project, out urls, out imgUrls);
}
//如果是百度图片网址则使用爬取贴吧图片的策略
else if (BaiduHTMLService.IsBaiduImgUrl(project.ImgInputData.Url))
{
CrawlBaiduImg(project.ImgInputData.Url, out imgUrls);
}
// 如果是微博网址则使用爬取微博图片的策略
else if (WeiboHTMLService.IsWeiboUrl(project.ImgInputData.Url))
{
//微博
CrawlWeiboImg(project.ImgInputData.Url, out imgUrls);
}
//如果是其他网址则使用爬取贴吧图片的策略
else
{
DefaultCrawl(project, out urls, out imgUrls);
}
foreach (string item in imgUrls)
{
if (true /*一些筛选条件*/)
{
project.URLData.ImgUrls.Enqueue(item);
}
}
ThreadCrawlDownload(project /*, urls, imgUrls)*/);
CrawlFinish();
return(true);
}
public static void TibaCrawl(Project project, out List <string> urls, out List <string> imgUrls)
{
//解析网页url
urls = TiebaHTMLService.TiebaParse(project.ImgInputData.Url);
//存储图片url
imgUrls = new List <string>();
foreach (string item in urls)
{
//生成一个0-1000内的随机数
int waitTime = new Random().Next(0, 1000);
//为防止网站的反爬机制，等待一个随机时间
Thread.Sleep(waitTime);
List <string> onePageImgUrl;
project.URLData.HTMLUrls.Enqueue(item);
//解析出该网页上的图片资源
string htmlcode = TiebaHTMLService.DownloadUrl(item);
onePageImgUrl = TiebaImgParse.GetImgUrls(htmlcode);
foreach (string imgurl in onePageImgUrl)
{
if (true /*一些筛选条件*/)
{
imgUrls.Add(imgurl);
}
}
}
////使用并行方式提高爬取速度
//ArrayList imgUrls = ArrayList.Synchronized(new ArrayList());
//Parallel.ForEach(urls, url => {
// string htmlCode = TiebaHTMLService.DownloadUrl(url);
// List<string> onePageImgUrls = TiebaHTMLService.Parse(htmlCode);
// foreach(string imgurl in onePageImgUrls)
// {
// imgUrls.Add(imgUrls);
// }
//});
}
