From 8d68ac7c900241eb8499a94c23ab1f60750e7aed Mon Sep 17 00:00:00 2001 From: horus Date: Fri, 15 Jun 2018 23:28:18 +0200 Subject: Introduces config for user agent, robots.txt and crawler delay. (crawler) --- crawler/shop_whiskyworld.go | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'crawler/shop_whiskyworld.go') diff --git a/crawler/shop_whiskyworld.go b/crawler/shop_whiskyworld.go index 7b57d37..3f0874d 100644 --- a/crawler/shop_whiskyworld.go +++ b/crawler/shop_whiskyworld.go @@ -15,7 +15,7 @@ func (app *App) ScrapeWhiskyworld(shop Shop) []Angebot { Whiskys := []Angebot{} - c := customCollector([]string{"whiskyworld.de", "www.whiskyworld.de"}) + c := app.customCollector([]string{"whiskyworld.de", "www.whiskyworld.de"}) c.OnHTML(".product-item", func(e *colly.HTMLElement) { if !stringInSlice(e.Request.URL.String(), Shop_urls) { @@ -123,7 +123,10 @@ func (app *App) ScrapeWhiskyworld(shop Shop) []Angebot { }) for _, url := range Shop_urls { - c.Visit(url) + err := c.Visit(url) + if err != nil { + Warn(nil, shop.Name+": "+err.Error()) + } } return Whiskys -- cgit v1.2.3