id2392-ensai/prix_restos
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Actualiser le_fooding_scraping.py

Browse Source
This commit is contained in:
Olivier MEYER 2024-06-27 11:04:04 +02:00
parent 8c4c54a42e
commit c9ad358993
1 changed files with 3 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
le_fooding_scraping.py
View File

@ -169,12 +169,11 @@ def scrap_page(url):
df = pd.DataFrame(list(zip(names, addresses, prices)), columns=['Name', 'Address', 'Price'])
for i in range(len(df)):
df.loc[i, 'Date'] = datetime.date.today()
print(df.to_string())
return df
# Main function
def main():
def complete_scraping():
ic()
# Initialization
starting_url = 'https://lefooding.com/recherche/restaurant/place/paris-8246'
@ -186,7 +185,6 @@ def main():
temporary_df = scrap_page(starting_url)
df = pd.concat([df, temporary_df], ignore_index=True)
print(df.to_string())
# Loop through the others pages
for i in range(2, number_of_pages+1):
@ -194,11 +192,8 @@ def main():
new_url = starting_url + '?page=' + str(i)
temporary_df = scrap_page(new_url)
df = pd.concat([df, temporary_df], ignore_index=True)
print(df.to_string())
df = df[~df['Name'].str.contains('style="display')]
return df
df = main()
df.to_csv('/Users/oliviermeyer/Desktop/le_fooding_test.csv', index=False, header=True, escapechar='\\')