Spaces:
Sleeping
Sleeping
Update Workflow/Scrape.py
Browse files- Workflow/Scrape.py +1 -1
Workflow/Scrape.py
CHANGED
|
@@ -6,7 +6,6 @@ import streamlit as st
|
|
| 6 |
import os
|
| 7 |
os.environ["INPUT_DATA"] = "Input/Sites.xlsx" ## to silence warning
|
| 8 |
|
| 9 |
-
places=[]
|
| 10 |
|
| 11 |
def get_inputData(filePath):
|
| 12 |
df= pd.read_excel(io=filePath, engine='openpyxl')
|
|
@@ -17,6 +16,7 @@ def open_url(url):
|
|
| 17 |
return result
|
| 18 |
|
| 19 |
def do_scrape(result):
|
|
|
|
| 20 |
soup = bs4.BeautifulSoup(result.text, "lxml")
|
| 21 |
for i in soup.select('h3'): places.append(i.getText())
|
| 22 |
return places
|
|
|
|
| 6 |
import os
|
| 7 |
os.environ["INPUT_DATA"] = "Input/Sites.xlsx" ## to silence warning
|
| 8 |
|
|
|
|
| 9 |
|
| 10 |
def get_inputData(filePath):
|
| 11 |
df= pd.read_excel(io=filePath, engine='openpyxl')
|
|
|
|
| 16 |
return result
|
| 17 |
|
| 18 |
def do_scrape(result):
|
| 19 |
+
places=[]
|
| 20 |
soup = bs4.BeautifulSoup(result.text, "lxml")
|
| 21 |
for i in soup.select('h3'): places.append(i.getText())
|
| 22 |
return places
|