app.py

import streamlit as st
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import json
import csv
import pandas as pd
import os
from gradio_client import Client

#api_key = os.getenv('groq')

def parse_links_and_content(ort):
    base_url = "https://vereine-in-deutschland.net"
    all_links = []   
    # Konstruiere die vollständige URL
    initial_url = f"{base_url}/vereine/Bayern/{ort}/"
    
    try:
        # Senden der Anfrage an die initiale URL
        response = requests.get(initial_url)
        response.raise_for_status()  # Überprüfen, ob die Anfrage erfolgreich war
        
        # Parse the HTML content using BeautifulSoup
        soup = BeautifulSoup(response.content, 'html.parser')
        
        # Ermittle die letzte Seite
        link_element = soup.select_one('li.page-item:nth-child(8) > a:nth-child(1)')
        
        if link_element and 'href' in link_element.attrs:
            href = link_element['href']
            # Extrahiere die letzten beiden Zeichen der URL
            last_two_chars = href[-2:]
            
            # Konvertiere die letzten beiden Zeichen in einen Integer
            last_two_chars_int = int(last_two_chars)
        else:
            last_two_chars_int = 1  # Falls die letzte Seite nicht gefunden wird, nimm an, dass es nur eine Seite gibt

        # Schleife durch alle Seiten und sammle Links
        for page_number in range(1, last_two_chars_int + 1):
            page_url = f"{base_url}/vereine/Bayern/{ort}/p/{page_number}"
            response = requests.get(page_url)
            response.raise_for_status()            
            soup = BeautifulSoup(response.content, 'html.parser')
            target_div = soup.select_one('div.row-cols-1:nth-child(4)')
            
            if target_div:
                texts = [a.text for a in target_div.find_all('a', href=True)] 
                all_links.extend(texts)
            else:
                st.write(f"Target div not found on page {page_number}")
        
    except Exception as e:
        return str(e), []
        
    all_links = all_links[0::2]
    return all_links

def scrape_links(links):
    contact_details = []
    client = Client("mgokg/PerplexicaApi")
    for verein in links:   
        result = client.predict(
            prompt=f"{verein}",
            api_name="/parse_links"
        )
        contact_details.append(result)
        
    return contact_details

# Speichere die JSON-Daten in eine CSV-Datei 
def save_to_csv(data, filename): 
    keys = data[0].keys() 
    with open(filename, 'w', newline='', encoding='utf-8') as output_file: 
        dict_writer = csv.DictWriter(output_file, fieldnames=keys) 
        dict_writer.writeheader() 
        dict_writer.writerows(data)

# Streamlit App
st.title("Vereinsinformationen abrufen")

ort_input = st.text_input("Ort", placeholder="Gib den Namen des Ortes ein")

if st.button("Senden"):
    links = parse_links_and_content(ort_input)
    contact_details = scrape_links(links)
    json_data = [json.loads(item) for item in contact_details]
    
    # Zeige die Ergebnisse an
    st.json(json_data)
    
    # Speichere die Daten in einer CSV-Datei
    save_to_csv(json_data, 'contact_details.csv')
    
    # Bereitstellung des Download-Links
    with open('contact_details.csv', 'rb') as file:
        st.download_button(
            label="CSV-Datei herunterladen",
            data=file,
            file_name='contact_details.csv',
            mime='text/csv'
        )












'''
import streamlit as st
#import sounddevice as sd
import numpy as np
import wavio
import speech_recognition as sr


st.title("Audio Recorder und Transkription")

# Aufnahmeparameter
duration = st.slider("Aufnahmedauer (Sekunden)", 1, 10, 5)
fs = 44100  # Abtastrate

if st.button("Aufnahme starten"):
    st.write("Aufnahme läuft...")
    #recording = sd.rec(int(duration * fs), samplerate=fs, channels=2)
    #sd.wait()  # Aufnahme beenden

    # Speichern der Aufnahme
    wavio.write("aufnahme.wav", recording, fs, sampwidth=2)
    st.write("Aufnahme abgeschlossen!")

    # Transkription
    recognizer = sr.Recognizer()
    with sr.AudioFile("aufnahme.wav") as source:
        audio_data = recognizer.record(source)
        try:
            text = recognizer.recognize_google(audio_data, language="de-DE")
            st.write("Transkribierter Text:")
            st.write(text)
        except sr.UnknownValueError:
            st.write("Audio konnte nicht erkannt werden.")
        except sr.RequestError as e:
            st.write(f"Fehler bei der Anfrage an den Google Speech Recognition Service: {e}")

# Hinweis für Benutzer
st.write("Klicke auf 'Aufnahme starten', um die Aufnahme zu beginnen.")







import streamlit as st
import pydub
import speech_recognition as sr
from io import BytesIO

st.title("Audio Recorder und Transkription")

# Audioaufnahme
audio_file = st.file_uploader("Lade eine Audiodatei hoch", type=["wav", "mp3"])

if audio_file is not None:
    audio_bytes = audio_file.read()
    audio = pydub.AudioSegment.from_file(BytesIO(audio_bytes))

    # Audio in das richtige Format konvertieren
    audio = audio.set_frame_rate(16000).set_channels(1).set_sample_width(2)
    audio_bytes = audio.raw_data

    # Audio transkribieren
    recognizer = sr.Recognizer()
    audio_source = sr.AudioData(audio_bytes, frame_rate=16000, sample_width=2, channels=1)
    try:
        text = recognizer.recognize_google(audio_source)
        st.write("Transkribierter Text:")
        st.write(text)
    except sr.UnknownValueError:
        st.write("Audio konnte nicht erkannt werden.")
    except sr.RequestError as e:
        st.write(f"Fehler bei der Anfrage an den Google Speech Recognition Service: {e}")

# Hinweis für Benutzer
st.write("Lade eine Audiodatei hoch, um sie zu transkribieren.")






import streamlit as st
from streamlit_webrtc import webrtc_streamer, AudioProcessorBase, WebRtcMode

class AudioProcessor(AudioProcessorBase):
    def recv(self, frame):
        # Hier kannst du die Audioverarbeitung hinzufügen
        return frame

st.title("Audio Recorder")

webrtc_ctx = webrtc_streamer(
    key="audio",
    mode=WebRtcMode.SENDRECV,
    audio_processor_factory=AudioProcessor,
    media_stream_constraints={"audio": True},
    async_processing=True,
)

if webrtc_ctx.state.playing:
    st.write("Recording...")
else:
    st.write("Click on Start to record audio.")



import streamlit as st
import os
import time
import pandas as pd
from pandasai import SmartDatalake
from pandasai import SmartDataframe
from pandasai.responses.streamlit_response import StreamlitResponse
import numpy as np
#from pandasai import Agent
import json
import matplotlib.pyplot as plt



os.environ['PANDASAI_API_KEY'] = "$2a$10$2s0v3C29vItNS2CO4QX10OV51/OONFCUNa4e9EU90w2Gozw88f4vK"
st.set_page_config(page_title="SAP Data Analysis", layout="wide")
st.image('Pandas-AI-Logo.png', caption=None)
uploaded_file = st.file_uploader("Upload CSV data for analysis", type=['csv'])
#uploaded_file = st.file_uploader("Upload EXcel data for analysis", type=['xlsx'])

df1 = ""
sdf = ""
data = [{"Feb 24":"","1.":"Do","2.":"Fr","3.":"Sa","4.":"So","5.":"Mo","6.":"Di","7.":"Mi","8.":"Do","9.":"Fr","10.":"Sa","11.":"So","12.":"Mo","13.":"Di","14.":"Mi","15.":"Do","16.":"Fr","17.":"Sa","18.":"So","19.":"Mo","20.":"Di","21.":"Mi","22.":"Do","23.":"Fr","24.":"Sa","25.":"So","26.":"Mo","27.":"Di","28.":"Mi","29.":"Do"},{"Feb 24":"Standke Steffen","1.":"F","2.":"F","3.":"","4.":"","5.":"","6.":"","7.":"","8.":"","9.":"","10.":"","11.":"","12.":"","13.":"","14.":"UA","15.":"UA","16.":"","17.":"SD","18.":"SD","19.":"","20.":"","21.":"","22.":"","23.":"","24.":"","25.":"","26.":"","27.":"","28.":"","29.":""},{"Feb 24":"Will Susanne","1.":"","2.":"TZ","3.":"","4.":"","5.":"UA","6.":"","7.":"","8.":"","9.":"TZ","10.":"","11.":"","12.":"","13.":"","14.":"","15.":"","16.":"TZ","17.":"","18.":"","19.":"","20.":"","21.":"","22.":"","23.":"TZ","24.":"","25.":"","26.":"","27.":"","28.":"","29.":""},{"Feb 24":"Raab Julia","1.":"TZ","2.":"TZ","3.":"","4.":"","5.":"","6.":"","7.":"","8.":"TZ","9.":"TZ","10.":"BLOCKER","11.":"","12.":"Ü","13.":"Ü","14.":"Ü","15.":"TZ","16.":"TZ","17.":"BLOCKER","18.":"","19.":"","20.":"","21.":"","22.":"TZ","23.":"TZ","24.":"","25.":"SD","26.":"","27.":"","28.":"","29.":"TZ"},{"Feb 24":"Eckert Marion","1.":"","2.":"","3.":"","4.":"","5.":"","6.":"","7.":"","8.":"","9.":"Ü","10.":"","11.":"","12.":"S","13.":"S","14.":"S","15.":"S","16.":"S","17.":"","18.":"","19.":"","20.":"","21.":"","22.":"","23.":"","24.":"","25.":"","26.":"S","27.":"S","28.":"S","29.":"S"},{"Feb 24":"Meder, Milena","1.":"","2.":"","3.":"","4.":"","5.":"","6.":"","7.":"","8.":"","9.":"","10.":"","11.":"","12.":"F","13.":"F","14.":"","15.":"F","16.":"F","17.":"","18.":"","19.":"","20.":"","21.":"","22.":"","23.":"","24.":"","25.":"","26.":"Voloreise","27.":"","28.":"","29.":""},{"Feb 24":"Despang Angelika","1.":"","2.":"","3.":"SD","4.":"","5.":"","6.":"","7.":"","8.":"","9.":"","10.":"","11.":"","12.":"UA","13.":"UA","14.":"UA","15.":"","16.":"","17.":"","18.":"","19.":"F","20.":"F","21.":"F","22.":"F","23.":"F","24.":"","25.":"","26.":"","27.":"","28.":"","29.":""},{"Feb 24":"Heike Beudert","1.":"TZ","2.":"0,5 U","3.":"","4.":"","5.":"TZ","6.":"","7.":"","8.":"","9.":"","10.":"SD","11.":"SD","12.":"UA","13.":"UA","14.":"TZ","15.":"TZ","16.":"TZ","17.":"","18.":"","19.":"TZ","20.":"TZ","21.":"TZ","22.":"TZ","23.":"TZ","24.":"","25.":"","26.":"F","27.":"F","28.":"F","29.":"F"},{"Feb 24":"Borst Benedikt","1.":"","2.":"","3.":"","4.":"SD","5.":"F","6.":"F","7.":"F","8.":"F","9.":"F","10.":"BLOCKER","11.":"","12.":"UA","13.":"UA","14.":"F","15.":"","16.":"","17.":"","18.":"","19.":"","20.":"","21.":"","22.":"","23.":"","24.":"BLOCKER","25.":"","26.":"","27.":"","28.":"","29.":""}]

#df = pd.DataFrame(data)
#sdf = SmartDataframe(df)
#df1

if uploaded_file is not None:
    
    #Dateien im CSV Format
    df1 = pd.read_csv(uploaded_file)
 
    # Dateien im XLSX Format
    #df1 = pd.read_excel(uploaded_file, sheet_name=NONE)
    #st.table(df1)
    df1 = pd.DataFrame(df1)
    st.success("Daten erfolgreich geladen!")
    df1
    #sdf = SmartDataframe(df1)
    

bild = st.empty()     
bild.subheader("Datenanalyse & Datenvisualisierung")
c = st.container(border=True)
prompt = st.text_area("Enter your prompt:")
if st.button("Generate"):

        if prompt:
            #c.text("Generating response...") 
            if os.path.isfile('./exports/charts/temp_chart.png'):
                os.remove('./exports/charts/temp_chart.png')
            #spin = st.spinner
            with c:
                with st.spinner("Generating response..."):
                    
                    #bar = st.progress(20)
                    
                    #bar = st.progress(100)
              
                    with bild:
                        sdf = SmartDataframe(df1)
                        st.write(sdf.chat(prompt))
                    #with st.spinner("Generating response..."):
                       
                        if os.path.isfile('./exports/charts/temp_chart.png'):
                            st.image('./exports/charts/temp_chart.png')

                         
                    #st.success('Done!')
                    #bar.progress(100)
                    
                #c.write(bar)
                #c.write(st.spinner)
                #bild.empty()
            
                #st.write(sdf.chat(prompt))            
            #bar.progress(100)
            

        else:

            st.error("Please enter a prompt.")



#with placeholder.container():
    #st.write("This is one element")
    #st.write("This is another")



#agent = Agent(df)
#result = agent.chat("erstelle balkendiagramm")
#st.write(result)
#sdf = SmartDataframe(df)
#sdf.chat("draw chart")
#pandas_ai = PandasAI(llm, verbose=True, save_charts=True)
#st.write(sdf.chat("Plot a chart"))
#st.write(st.bar_chart(data))
'''