Spaces:
Build error
Build error
Update tariff_scraper.py
Browse files- tariff_scraper.py +7 -36
tariff_scraper.py
CHANGED
|
@@ -1,8 +1,7 @@
|
|
| 1 |
-
import streamlit as st
|
| 2 |
import requests
|
| 3 |
from bs4 import BeautifulSoup
|
| 4 |
|
| 5 |
-
# Dictionary
|
| 6 |
TARIFF_URLS = {
|
| 7 |
"IESCO": "https://iesco.com.pk/index.php/customer-services/tariff-guide",
|
| 8 |
"FESCO": "https://fesco.com.pk/tariff",
|
|
@@ -14,16 +13,17 @@ TARIFF_URLS = {
|
|
| 14 |
"TESCO": "https://tesco.gov.pk/index.php/electricity-tariff"
|
| 15 |
}
|
| 16 |
|
| 17 |
-
# Function to scrape tariff data from a given URL
|
| 18 |
def scrape_tariff_data(url):
|
|
|
|
|
|
|
|
|
|
| 19 |
try:
|
| 20 |
response = requests.get(url, headers={"User-Agent": "Mozilla/5.0"})
|
| 21 |
response.raise_for_status() # Raise an error for bad responses
|
| 22 |
soup = BeautifulSoup(response.text, 'html.parser')
|
| 23 |
|
| 24 |
# Extract specific elements based on the webpage structure
|
| 25 |
-
# Assume tariff data is in <table> tags
|
| 26 |
-
tariff_sections = soup.find_all('table')
|
| 27 |
|
| 28 |
data = []
|
| 29 |
for section in tariff_sections:
|
|
@@ -35,35 +35,6 @@ def scrape_tariff_data(url):
|
|
| 35 |
if row_text: # Add the row text only if it contains data
|
| 36 |
data.append(row_text)
|
| 37 |
|
| 38 |
-
return data
|
| 39 |
except Exception as e:
|
| 40 |
-
return f"An error occurred: {e}"
|
| 41 |
-
|
| 42 |
-
# Streamlit app main function
|
| 43 |
-
def main():
|
| 44 |
-
st.title("Electricity Tariff Scraper")
|
| 45 |
-
st.write("Select the company to fetch tariff rates:")
|
| 46 |
-
|
| 47 |
-
# Dropdown menu for company selection
|
| 48 |
-
company = st.selectbox("Select Company", list(TARIFF_URLS.keys()))
|
| 49 |
-
|
| 50 |
-
if st.button("Scrape"):
|
| 51 |
-
if company:
|
| 52 |
-
url = TARIFF_URLS[company] # Get the URL for the selected company
|
| 53 |
-
st.write(f"Scraping data for: **{company}**")
|
| 54 |
-
with st.spinner("Scraping data..."):
|
| 55 |
-
data = scrape_tariff_data(url)
|
| 56 |
-
if isinstance(data, list) and data:
|
| 57 |
-
st.success("Data scraped successfully!")
|
| 58 |
-
st.write("Here is a preview of the data:")
|
| 59 |
-
for row in data[:10]: # Show only the first 10 rows for readability
|
| 60 |
-
st.write(row)
|
| 61 |
-
elif isinstance(data, list) and not data:
|
| 62 |
-
st.warning("No data found on the page.")
|
| 63 |
-
else:
|
| 64 |
-
st.error(data)
|
| 65 |
-
else:
|
| 66 |
-
st.error("Please select a valid company.")
|
| 67 |
-
|
| 68 |
-
if __name__ == "__main__":
|
| 69 |
-
main()
|
|
|
|
|
|
|
| 1 |
import requests
|
| 2 |
from bs4 import BeautifulSoup
|
| 3 |
|
| 4 |
+
# Dictionary mapping companies to their URLs
|
| 5 |
TARIFF_URLS = {
|
| 6 |
"IESCO": "https://iesco.com.pk/index.php/customer-services/tariff-guide",
|
| 7 |
"FESCO": "https://fesco.com.pk/tariff",
|
|
|
|
| 13 |
"TESCO": "https://tesco.gov.pk/index.php/electricity-tariff"
|
| 14 |
}
|
| 15 |
|
|
|
|
| 16 |
def scrape_tariff_data(url):
|
| 17 |
+
"""
|
| 18 |
+
Scrape tariff data from the given URL.
|
| 19 |
+
"""
|
| 20 |
try:
|
| 21 |
response = requests.get(url, headers={"User-Agent": "Mozilla/5.0"})
|
| 22 |
response.raise_for_status() # Raise an error for bad responses
|
| 23 |
soup = BeautifulSoup(response.text, 'html.parser')
|
| 24 |
|
| 25 |
# Extract specific elements based on the webpage structure
|
| 26 |
+
tariff_sections = soup.find_all('table') # Assume tariff data is in <table> tags
|
|
|
|
| 27 |
|
| 28 |
data = []
|
| 29 |
for section in tariff_sections:
|
|
|
|
| 35 |
if row_text: # Add the row text only if it contains data
|
| 36 |
data.append(row_text)
|
| 37 |
|
| 38 |
+
return data if data else ["No data found on the webpage."]
|
| 39 |
except Exception as e:
|
| 40 |
+
return [f"An error occurred: {e}"]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|