func DownloadRecipesFromUrls(urls []string) DownloadRecipesResult {
result := DownloadRecipesResult{}
result.URLs = make([]string, 0)
result.URLsWithoutRecipes = make([]string, 0)
visited := make(map[string]bool)
for len(urls) > 0 {
url := urls[0]
urls = urls[1:]
if visited[url] {
continue
}
visited[url] = true
articleId := lib.GetArticleId(url)
if articleId < 1 {
recipeDebugger.Println("Skipped, cannot determine article ID")
continue
}
extracted := extraction.ExtractDataFromHTMLAtURL(url, false)
recipesInArticle := extracted.RecipeData.Recipes
for _, recipe := range recipesInArticle {
recipe.ArticleId = articleId
}
if recipeDebugger.IsEnabled() {
fmt.Printf("Found %d recipes + %d links in %s\n", len(recipesInArticle), len(extracted.RecipeData.EmbeddedArticleUrls), url)
}
if len(recipesInArticle) == 0 && len(extracted.RecipeData.EmbeddedArticleUrls) == 0 {
result.URLsWithoutRecipes = append(result.URLsWithoutRecipes, url)
}
result.URLs = append(result.URLs, url)
if false {
for i, recipe := range result.Recipes {
recipeDebugger.Println()
recipeDebugger.Println("Recipe ", i, "=", recipe.String())
recipeDebugger.Println()
}
}
result.Recipes = append(result.Recipes, extracted.RecipeData.Recipes...)
urls = append(urls, extracted.RecipeData.EmbeddedArticleUrls...)
}
return result
}
package commands
import (
"strings"
"time"
"github.com/michigan-com/newsfetch/extraction"
"github.com/michigan-com/newsfetch/lib"
"github.com/spf13/cobra"
)
var cmdBody = &cobra.Command{
Use: "body",
Short: "Get article body content from Gannett URL",
Run: func(cmd *cobra.Command, args []string) {
startTime = time.Now()
if len(args) > 0 && args[0] != "" {
articleUrl = args[0]
}
extracted := extraction.ExtractDataFromHTMLAtURL(articleUrl, includeTitle)
bodyFmt := strings.Join(strings.Split(extracted.Text, "\n"), "\n\n")
lib.Logger.Println(bodyFmt)
getElapsedTime(&startTime)
},
}
