From 2f5ed60ffbbd948a815f1b2ef3ecfd19c35f6cf3 Mon Sep 17 00:00:00 2001
From: Ebbe <ebbe@ping-mee.de>
Date: Tue, 25 Aug 2026 23:55:40 +0200
Subject: [PATCH] Wrote scraper for fundbureau website

---
 .DS_Store          | Bin 0 -> 8196 bytes
 scraper/scraper.py | 112 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 112 insertions(+)
 create mode 100644 .DS_Store
 create mode 100644 scraper/scraper.py

diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..d8cd8968d9c99de61b5b08a6f7ce2fac48fa3341
GIT binary patch
literal 8196
zcmeHMU2GIp6u#fI&>1?=0SXk{2@8cFWPuh+TK>%TPx&vfE!~!%Wp-zz1JjwZGrKL6
z#>T`%Q7}Gf{DmitMji~H@kJ9A(MLrSjPZe}QC~387nKLk%$+6B(!>~JY@D0SJ@?*o
z&b{}X`M#OGvy3sc6!dz=Y8Yc8UA|N*sk%q;_5L-k2;oRMNsvEd1I%Fg?4Uc4wZ>UT
z15pN|3`7}-G7x1T%D{gi1N6@Ji#Wl1pKGH!%0QHX|78aJ=R=$>UnWC2%4P8Apei^5
zko1oLL7_IC0|K9TD3hTa<uY)kIr-@Up)0~82Dm%v<Gwk`WGF|u<n9dIogrKq;Ryx7
z>f{#>%o&ngMs<{dC<Eg&;M1pqxh%)>OuO^^?qo@GIXhsPu2)z0C4{o_DN`%N3b9f=
znCf!|Q=aA(+!igr-|uxgj+HI7wd_9A7|bZut&Z(!rfuW{2U9o5<UqG+>&{?{Q?PY6
z@J(@rD2Y-=nL9jOmx!-hKaz+K*Ecj!yQ#i@WJD6@)UMvRH*?JDx1Gm%7ziH)Z2Fk6
zo){mK<rZ7BmLF4Dsua^#rI@5?mGX48JKfW}U(P7AinRHT0nc=7cb}1WNoJHPmxA1y
zbL`!D!`FA`9IMc8yBTF>PP1|aOY@9o%SxFi4H~O*b9u+Ib~~==Pt%k3j3Lk0jZ>w2
zT_^9g29u>tnx9)K1=rYX(4=P3Xrrm!>M<cgx-etj!X@{wT+_HI*}iq>o@-Ug%vrOm
zWx1EKX?y0wrjhR&G<C19M{{$At(*3d?xN|MS<C3OwSHqJ5|VVSs%HLz`(mm(k!iY+
zHIEle?}Sn-ioqK3MXG#2r#<a-bbl3Hxg^p&wEEITs=D9TwB`+}_0VDY3RUiODR@N-
z4Ogv}<<4US1I6{XK(1>WWVOrEvWBJT5?`ljy{vW@dH$8{;o#<KSxx7h{(cJ44ab^W
zRP~U*><-QKItC1zwsbXI`$5w6x_w&S=olmzhNIhPG`OWS?mM;Xrso7o%Em5=qQ{@E
zS=WOY7SznIQd4S|sC*`76vecQCPANWD`$XMTe>y1$rZd=`~I<WK`TgfZL*FJOZ19U
z*&5cycCf=lw_$dMJ;%<oi|iwIg?+)kVL!5)>^A^YAz>OSQH=#yf&|u~5lvW+7Ia__
z_9BG?=!1!)a503F7{)0)hSPWoXK)tJ;w8L-b2yLJ@fI%P5-#ICT*W8&6rbY;zQuR=
z9yjqj{=h9^iZD;85#|evg@mwDSS2(HO~M9Yqp(Zp5YmDs92Fd4hzB5)2zQY8OSN!<
zT4Np}L^%2g=o3!3aBsrJ9@?^X+xE#rxa%`G#pcYN7hk$!bwktU=G#!@*e${JP7(yj
zzl$#c@&jayLG3lpMR{R~r(;RkMU*jyM4!1z1-D)-FA<3{$`syRCNCF>EXq{gO~h7-
zL{CKsx^jJNtwbbL%6K;sYm`I<yt6^xBoQ5za^6+tq$DXU=)_uM?IKZ15&tQyUuQSi
z5A0`li?BWevr&U(s3U|wfGyZX821t0g+s_dLl!#vVPgQt3GJsaf=4ilNAV<~{Vblw
zGk6{^;6=QQSMeGl{tdiIcz+x3;9Y!x4{-$_hsgh$aQ_p28H44WB@}asU&mv)n9AFh
zV;><+i2-*zP10T&-*=6F{%@c7`~M`3F4}gKfhYriB?BmLOSQF-<wQ?6fpl@Y4%6iq
z-)@x4z=bN`#2*ii<0NnYVMy(Gs7r=&luOc3`PV-L{M{ei(fdDo{|CqqU_0rnKLPdj
Bc9H-9

literal 0
HcmV?d00001

diff --git a/scraper/scraper.py b/scraper/scraper.py
new file mode 100644
index 0000000..8967d6b
--- /dev/null
+++ b/scraper/scraper.py
@@ -0,0 +1,112 @@
+import argparse
+from bs4 import BeautifulSoup
+import json
+from playwright.sync_api import sync_playwright
+
+scrape_url = "https://fundbureau.de/"
+load_local_file = False
+output_file = "fundi-scraped-output.json"
+output_path = "./"
+ignore_ticket_link = False
+
+argp = argparse.ArgumentParser()
+argp.add_argument("--url", type=str, help="URL to scrape (default: https://fundbureau.de/)")
+argp.add_argument("--output-file", type=str, help="Output JSON file name (default: fundi-scraped-output.json)")
+argp.add_argument("--output-path", type=str, help="Output path for the JSON file (default: current directory)")
+argp.add_argument("--load-local-file", action="store_true", help="Load local HTML file instead of scraping the website (default: False)")
+argp.add_argument("--ignore-ticket-link", action="store_true", help="Ignore ticket link extraction (will leave it empty in the output JSON)")
+args = argp.parse_args()
+
+if vars(args)["url"]:
+    scrape_url = vars(args)["url"]
+if vars(args)["output_file"]:
+    output_file = vars(args)["output_file"]
+if vars(args)["output_path"]:
+    output_path = vars(args)["output_path"]
+if vars(args)["load_local_file"]:
+    load_local_file = True
+if vars(args)["ignore_ticket_link"]:
+    ignore_ticket_link = True
+
+# -------------
+# START OF AI WRITTEN SECTION (Claude Pro, Sonnet 5 medium)
+
+def scrape_website(url, load_local_file):
+    if load_local_file == True:
+        with open(url) as file:
+            soup = BeautifulSoup(file, "html.parser")
+        return soup
+    else:
+        with sync_playwright() as p:
+            browser = p.chromium.launch(headless=True)
+            page = browser.new_page()
+            page.goto(url, wait_until="networkidle")
+            try:
+                # Wait until at least one .event div actually renders in the DOM
+                page.wait_for_selector("#upcoming-events-container .event", timeout=15000)
+            except Exception:
+                print("Warning: no .event elements appeared before timeout.")
+            html = page.content()
+            browser.close()
+
+        soup = BeautifulSoup(html, "html.parser")
+        return soup
+
+# END OF AI WRITTEN SECTION (Claude Pro, Sonnet 5 medium)
+# -------------
+        
+def extract_events(soup, ignore_ticket_link):
+    events = soup.find_all("div", class_="event")
+    events_processed = []
+    for event in events:
+        event_date = event.find("div", class_="event-date").text.strip()
+        event_name = event.find("div", class_="event-name").text.strip()
+        
+        event_artists_datalist = event.find("div", class_="event-artists")
+        event_artists_datalist = str(event_artists_datalist).removeprefix('<div class="event-artists">').removesuffix("</div>").split(", ")
+        
+        event_artists = []
+
+        for event_artist_data in event_artists_datalist:
+            if "<sup>" in event_artist_data:
+                event_artist_data = event_artist_data.split("<sup>")
+                artist_name = event_artist_data[0]
+                artist_time = event_artist_data[1].removesuffix("</sup>").replace("?", "Open end").split("-")
+                event_artists.append({
+                    "artist_name": event_artist_data[0],
+                    "artist_play_time_start": artist_time[0],
+                    "artist_play_time_end": artist_time[1]
+                })
+            else:
+                artist_name = event_artist_data
+                event_artists.append({
+                    "artist_name": event_artist_data,
+                    "artist_play_time_start": "n/a",
+                    "artist_play_time_end": "n/a"
+                })
+
+
+        event_starttime = event.find("div", class_="event-starttime").text.strip()
+        if ignore_ticket_link:
+            event_ticket_link = ""
+        else:
+            event_ticket_link = event.find("a", class_="event-ticket-link")["href"]
+
+        json_data = {
+            "event_date": event_date,
+            "event_name": event_name,
+            "event_artists": [event_artists],
+            "event_starttime": event_starttime,
+            "event_ticket_link": event_ticket_link
+        }
+
+        events_processed.append(json_data)
+    with open(output_path + output_file, "w") as json_file:
+        json.dump(events_processed, json_file, indent=4)
+
+def main():
+    soup = scrape_website(scrape_url, load_local_file)
+    extract_events(soup, ignore_ticket_link)
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file