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

Actualiser google_scraping.py

Browse Source
This commit is contained in:
Olivier MEYER 2024-06-27 11:48:18 +02:00
parent 5740be9bbc
commit 70d581758b
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
google_scraping.py
View File

@ -19,7 +19,7 @@ def google_scrap_fooding(df):
url = base_url + str(name).replace(' ', '-') + str(address).replace(' ', '-') url = base_url + str(name).replace(' ', '-') + str(address).replace(' ', '-')
ic() ic()
ic(url) ic(name)
driver.get(url) driver.get(url)
time.sleep(0.1) time.sleep(0.1)
@ -69,14 +69,13 @@ def google_scrap_fute(df):
ic() ic()
for name, address in zip(df['Name'], df['Address']): for name, address in zip(df['Name'], df['Address']):
ic() ic()
ic(name)
options = webdriver.ChromeOptions() options = webdriver.ChromeOptions()
options.add_argument("---headless=True") options.add_argument("---headless=True")
driver = webdriver.Chrome(options=options) driver = webdriver.Chrome(options=options)
base_url = 'https://www.google.com/search?hl=en&q=' base_url = 'https://www.google.com/search?hl=en&q='
try: try:
url = base_url + name.replace(' ', '-') + address.replace(' ', '-') url = base_url + name.replace(' ', '-') + address.replace(' ', '-')
ic(url)
driver.get(url) driver.get(url)
time.sleep(0.1) time.sleep(0.1)