Пример #1
0
// extracts the URL from an Feed. If the feed has publication date, we only
// add the URL since the last feed update
func getLinksFromFeed(dsFeed *data.Feed, r *http.Request, c appengine.Context) ([]string, error) {
	c.Infof("DS Feed @ importer: %v", dsFeed)
	_, body, err := extract.GetURL(dsFeed.URL, r)
	if err != nil {
		return nil, err
	}

	rss, err := parseFeedContent(body)
	if err != nil {
		return nil, err
	}

	var urls []string
	stopURL := dsFeed.LastURL
	for index, i := range rss.ItemList {
		if index == 0 {
			dsFeed.LastURL = i.Link
		}
		if i.Link == stopURL {
			break
		}
		urls = append(urls, i.Link)
	}

	return urls, nil
}
Пример #2
0
// DispatchPOST updates the rss feed passed via post
func DispatchPOST(w http.ResponseWriter, r *http.Request) {
	c := appengine.NewContext(r)

	defer r.Body.Close()

	if err := r.ParseForm(); err != nil {
		c.Errorf("Error at in updatePost @ ParseForm. Error: %v", err)
		w.WriteHeader(http.StatusInternalServerError)
		return
	}

	dsFeed, err := data.FeedStored(c, r.FormValue("url"))

	// get the url from the datastore
	if err != nil {
		c.Errorf("Error getting the url from the DS: %v", err)
		w.WriteHeader(http.StatusInternalServerError)
		return
	}

	if dsFeed == nil {
		c.Errorf("Got no feed from the DS: %v", err)
		w.WriteHeader(http.StatusInternalServerError)
		return
	}

	importURL := config.KaffeeshareURL + "/k/share/json/" + dsFeed.Namespace
	importURL += "/?url=" + url.QueryEscape("https://kaffeebot.com/stops/updating/goodbye")
	c.Infof("URL we get %v", importURL)
	_, body, err := extract.GetURL(importURL, r)
	if err != nil {
		c.Errorf("Error while importing url into namespace: %v, %v", importURL, err)
		// we'll ignore the errors for now
		// actually we may want to offload this into another task queue for easier retries
	} else {
		c.Infof("body: %v", string(body))
	}

	w.WriteHeader(http.StatusOK)
}
Пример #3
0
// DispatchPOST updates the rss feed passed via post
func DispatchPOST(w http.ResponseWriter, r *http.Request) {
	c := appengine.NewContext(r)

	defer r.Body.Close()

	if err := r.ParseForm(); err != nil {
		c.Errorf("Error at in updatePost @ ParseForm. Error: %v", err)
		w.WriteHeader(http.StatusInternalServerError)
		return
	}

	dsFeed, err := data.FeedStored(c, r.FormValue("url"))

	// get the url from the datastore
	if err != nil {
		c.Errorf("Error getting the url from the DS: %v", err)
		w.WriteHeader(http.StatusInternalServerError)
		return
	}

	if dsFeed == nil {
		c.Errorf("Got no feed from the DS: %v", err)
		w.WriteHeader(http.StatusInternalServerError)
		return
	}

	// read the url
	c.Infof("DS Feed @ importer: %v", dsFeed)

	// parse feed
	urls, err := getLinksFromFeed(dsFeed, r, c)
	if err != nil {
		c.Errorf("Error parsing the url: %v", dsFeed.URL)
		dsFeed.Fails++
		err := data.StoreFeed(c, *dsFeed)
		if err != nil {
			c.Errorf("Error while updating url %v in the DS: %v", dsFeed.URL, err)
		}

		w.WriteHeader(http.StatusInternalServerError)
		return
	}

	c.Infof("URLs found in feed: %v", urls)

	dsFeed.LastUpdate = time.Now() // update time of the last update

	// put urls into kshare
	for _, u := range urls {
		importURL := config.KaffeeshareURL + "/k/share/json/" + dsFeed.Namespace //"test"
		importURL += "/?url=" + url.QueryEscape(u)
		c.Infof("URL we get %v", importURL)
		_, body, err := extract.GetURL(importURL, r)
		if err != nil {
			c.Errorf("Error while importing url into namespace: %v, %v", importURL, err)
			// we'll ignore the errors for now
			// actually we may want to offload this into another task queue for easier retries
		} else {
			c.Infof("body: %v", string(body))
		}
	}

	// update feed in DS
	dsFeed.Fails = 0 // reset error count

	err = data.StoreFeed(c, *dsFeed)
	if err != nil {
		c.Errorf("Error while updating url %v in the DS: %v", dsFeed.URL, err)
	}
	w.WriteHeader(http.StatusOK)
}