Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -3,8 +3,6 @@ from bs4 import BeautifulSoup
|
|
3 |
import pandas as pd
|
4 |
import plotly.graph_objects as go
|
5 |
import streamlit as st
|
6 |
-
from geopy.geocoders import Nominatim
|
7 |
-
from geopy.exc import GeocoderServiceError
|
8 |
|
9 |
# 設定應用標題
|
10 |
st.title("餐廳資料抓取與分析")
|
@@ -19,51 +17,32 @@ urls = urls_df['網址'].tolist()
|
|
19 |
# 初始化一個空的 DataFrame 列表來儲存所有資料
|
20 |
df_list = []
|
21 |
|
22 |
-
# 初始化 geolocator
|
23 |
-
geolocator = Nominatim(user_agent="restaurant_data_app")
|
24 |
-
|
25 |
# 迭代每個網址並抓取資料
|
26 |
for url in urls:
|
27 |
try:
|
28 |
response = requests.get(url)
|
29 |
-
response.raise_for_status()
|
30 |
soup = BeautifulSoup(response.content, 'html.parser')
|
31 |
|
32 |
# 解析並抓取所需資料
|
33 |
title_tag = soup.find('h1', class_='restaurant-details__heading--title')
|
34 |
title = title_tag.text.strip() if title_tag else 'N/A'
|
35 |
-
|
36 |
address_tag = soup.find('li', class_='restaurant-details__heading--address')
|
37 |
address = address_tag.text.strip() if address_tag else 'N/A'
|
38 |
-
|
39 |
phone_tag = soup.find('a', {'data-event': 'CTA_tel'})
|
40 |
phone = phone_tag['href'].replace('tel:', '') if phone_tag else 'N/A'
|
41 |
-
|
42 |
description_tag = soup.find('div', class_='restaurant-details__description--text')
|
43 |
description = description_tag.text.strip() if description_tag else 'N/A'
|
44 |
|
45 |
-
# Geocoding the address
|
46 |
-
try:
|
47 |
-
location = geolocator.geocode(address)
|
48 |
-
latitude = location.latitude if location else 'N/A'
|
49 |
-
longitude = location.longitude if location else 'N/A'
|
50 |
-
except GeocoderServiceError:
|
51 |
-
latitude = 'N/A'
|
52 |
-
longitude = 'N/A'
|
53 |
-
|
54 |
# 將抓取的資料新增到列表中
|
55 |
-
df_list.append({
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
'Latitude': latitude,
|
61 |
-
'Longitude': longitude
|
62 |
-
})
|
63 |
-
except requests.HTTPError as http_err:
|
64 |
-
st.error(f"HTTP error occurred for URL {url}: {http_err}")
|
65 |
-
except Exception as err:
|
66 |
-
st.error(f"An error occurred for URL {url}: {err}")
|
67 |
|
68 |
# 使用 pd.DataFrame() 將所有資料合併成一個 DataFrame
|
69 |
df = pd.DataFrame(df_list)
|
@@ -90,4 +69,3 @@ fig_pie.update_layout(title='每個區的商家數量比例')
|
|
90 |
# 按鈕來顯示圓餅圖
|
91 |
if st.button('顯示每個區的商家數量比例圓餅圖'):
|
92 |
st.plotly_chart(fig_pie)
|
93 |
-
|
|
|
3 |
import pandas as pd
|
4 |
import plotly.graph_objects as go
|
5 |
import streamlit as st
|
|
|
|
|
6 |
|
7 |
# 設定應用標題
|
8 |
st.title("餐廳資料抓取與分析")
|
|
|
17 |
# 初始化一個空的 DataFrame 列表來儲存所有資料
|
18 |
df_list = []
|
19 |
|
|
|
|
|
|
|
20 |
# 迭代每個網址並抓取資料
|
21 |
for url in urls:
|
22 |
try:
|
23 |
response = requests.get(url)
|
24 |
+
response.raise_for_status() # Raises an HTTPError for bad responses
|
25 |
soup = BeautifulSoup(response.content, 'html.parser')
|
26 |
|
27 |
# 解析並抓取所需資料
|
28 |
title_tag = soup.find('h1', class_='restaurant-details__heading--title')
|
29 |
title = title_tag.text.strip() if title_tag else 'N/A'
|
30 |
+
|
31 |
address_tag = soup.find('li', class_='restaurant-details__heading--address')
|
32 |
address = address_tag.text.strip() if address_tag else 'N/A'
|
33 |
+
|
34 |
phone_tag = soup.find('a', {'data-event': 'CTA_tel'})
|
35 |
phone = phone_tag['href'].replace('tel:', '') if phone_tag else 'N/A'
|
36 |
+
|
37 |
description_tag = soup.find('div', class_='restaurant-details__description--text')
|
38 |
description = description_tag.text.strip() if description_tag else 'N/A'
|
39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
# 將抓取的資料新增到列表中
|
41 |
+
df_list.append({'Title': title, 'Address': address, 'Phone': phone, 'Description': description})
|
42 |
+
|
43 |
+
except requests.exceptions.HTTPError as e:
|
44 |
+
print(f"HTTP error occurred for URL {url}: {e}")
|
45 |
+
continue # Skip to the next URL if there's an error
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
# 使用 pd.DataFrame() 將所有資料合併成一個 DataFrame
|
48 |
df = pd.DataFrame(df_list)
|
|
|
69 |
# 按鈕來顯示圓餅圖
|
70 |
if st.button('顯示每個區的商家數量比例圓餅圖'):
|
71 |
st.plotly_chart(fig_pie)
|
|