Esempio n. 1
0
        public GeneralSiteCrawler(SiteParameter siteParameter)
        {
            IItemReader itemReader = new RegexItemReader(siteParameter);

            IHtmlReader htmlReader = new HttpClientReader();

            this.pageReader = new SequentialPageReader(siteParameter, htmlReader, itemReader);
            this.pageParser = new RegexPageParser(siteParameter, htmlReader);
        }
Esempio n. 2
0
        public GeneralSiteCrawler(SiteParameter siteParameter)
        {
            this.dataService = new DbDataService(CrawlerDbHelper.GetContext());
            IItemReader itemReader = new RegexItemReader(siteParameter);

            IHtmlReader htmlReader = new HttpClientReader();

            this.pageReader = new SequentialPageReader(siteParameter, htmlReader, itemReader);
            this.pageParser = new RegexPageParser(siteParameter, htmlReader);
            this.pageParser.SetErrorHandler((url, exception) =>
                                            this.dataService.AddLog(new CrawlerLog
            {
                Url     = url,
                LogTime = DateTime.Now,
                Message = exception.Message
            }));
        }