From 2fb591dc53f024b199b8d272784077eccdc11b37 Mon Sep 17 00:00:00 2001 From: Mark Andrew Jaroski Date: Tue, 26 May 2026 19:36:07 +0200 Subject: [PATCH 1/2] Added an imageUrl to all functional scrapers I also created issues for the non-functional ones, at least most of them --- config/zurich.yml | 62 +++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 57 insertions(+), 5 deletions(-) diff --git a/config/zurich.yml b/config/zurich.yml index ef07ee3..896ecd8 100644 --- a/config/zurich.yml +++ b/config/zurich.yml @@ -118,6 +118,11 @@ scrapers: - name: "title" location: selector: ".text-block-21" + - name: "imageUrl" + type: "url" + location: + selector: "img" + attr: "src" - name: "comment" location: selector: ".text-block-28" @@ -157,6 +162,12 @@ scrapers: selector: h3.h3 all_nodes: true separator: ", " + - name: imageUrl + type: url + location: + - selector: div > div.w-full > span > span.hidden > span > div > img:nth-child(2) + attr: src + can_be_empty: true - name: url type: url location: @@ -324,6 +335,13 @@ scrapers: type: "url" location: selector: ".event-link" + - name: "imageUrl" + type: "url" + on_subpage: "url" + location: + selector: "figure.event-media-image > img" + attr: src + can_be_empty: true - name: "date" type: "date" on_subpage: "url" @@ -385,6 +403,9 @@ scrapers: type: "url" location: selector: ".desktop-linkoverlay" + - name: "imageUrl" + type: "url" + value: "https://www.tonhalle-orchester.ch/site/templates/images/TonhalleZurich_Logo_RGB_Schwarz.png" - name: "date" type: "date" components: @@ -553,6 +574,11 @@ scrapers: type: "url" location: selector: ".col-sm-8 h2 a" + - name: "imageUrl" + type: "url" + location: + selector: "img.img-responsive" + attr: "src" - name: "comment" on_subpage: "url" can_be_empty: true @@ -802,6 +828,13 @@ scrapers: type: "url" location: selector: "a" + - name: "imageUrl" + on_subpage: "url" + type: "url" + location: + selector: "div.image > img" + attr: "src" + can_be_empty: true - name: "date" type: "date" components: @@ -1348,7 +1381,7 @@ scrapers: - name: AlteKaserne url: https://www.altekaserne.com/events - item: div.row.party > div.col-sm-8.col-lg-9 > div.text-block + item: div.row.party fields: - name: "type" value: "concert" @@ -1363,8 +1396,14 @@ scrapers: - name: url type: url location: - - selector: a + - selector: div.text-block > a attr: href + - name: imageUrl + type: url + location: + - selector: div.img-block > a > img + attr: src + can_be_empty: true - name: date type: date components: @@ -1373,7 +1412,7 @@ scrapers: month: true year: true location: - selector: a > div.datum + selector: div.text-block > a > div.datum layout: ["Mon. 2. Jan. 2006"] - covers: time: true @@ -1388,11 +1427,11 @@ scrapers: - name: title type: text location: - - selector: a > h3.name + - selector: div.text-block > a > h3.name - name: comment type: text location: - - selector: p + - selector: div.text-block > p - name: MaagMoments url: https://www.maag-moments.ch/maag/de/events.html?event_category=konzerte @@ -1566,6 +1605,9 @@ scrapers: value: https://baramegge.ch/programm/konzerte/ - name: url value: https://baramegge.ch/programm/konzerte/ + - name: imageUrl + type: url + value: https://baramegge.ch/wp-content/uploads/yootheme/cache/86/BaE_Logo_RGB-860b4f19.webp - name: location value: Bar Am Egge - name: comment @@ -1735,6 +1777,13 @@ scrapers: location: - selector: div.heading-container:nth-child(2) > h2.heading > a attr: href + - name: imageUrl + type: url + location: + - selector: picture > img + attr: data-srcset + regex_extract: + exp : "[^, ]+" - name: date type: date components: @@ -2624,6 +2673,9 @@ scrapers: value: concert - name: sourceUrl value: https://www.galotti.ch/events/ + - name: imageUrl + value: https://p.kagi.com/proxy/01_logo_galotti_schwarz-weiss.240x0.png + type: url - name: title type: text location: From a29e35a6cac7734eaf0e5bb97c45e73d72846cef Mon Sep 17 00:00:00 2001 From: Mark Andrew Jaroski Date: Fri, 10 Jul 2026 10:22:01 +0200 Subject: [PATCH 2/2] Fixed Moods and Tonhalle imageUrls For Moods the fix was to change the type to text, as goskyr doesn't recognize the URL protocol "data". For Tonhalle we're now getting the image used as the banner on the event page, whereas I had lazily settled for the logo. --- config/zurich.yml | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/config/zurich.yml b/config/zurich.yml index 896ecd8..db3ac48 100644 --- a/config/zurich.yml +++ b/config/zurich.yml @@ -163,7 +163,7 @@ scrapers: all_nodes: true separator: ", " - name: imageUrl - type: url + type: text location: - selector: div > div.w-full > span > span.hidden > span > div > img:nth-child(2) attr: src @@ -405,7 +405,11 @@ scrapers: selector: ".desktop-linkoverlay" - name: "imageUrl" type: "url" - value: "https://www.tonhalle-orchester.ch/site/templates/images/TonhalleZurich_Logo_RGB_Schwarz.png" + on_subpage: url + location: + selector: div.pagetitle-header > img + attr: src + default: "https://www.tonhalle-orchester.ch/site/templates/images/TonhalleZurich_Logo_RGB_Schwarz.png" - name: "date" type: "date" components: