Update scrap.py
Browse files
scrap.py
CHANGED
|
@@ -1,17 +1,30 @@
|
|
| 1 |
import time
|
|
|
|
| 2 |
from selenium.webdriver import Chrome
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
from selenium.webdriver.common.by import By
|
| 4 |
|
| 5 |
def extract(link):
|
| 6 |
url = link
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
data = data.text
|
| 12 |
data = data.split("\n")
|
| 13 |
time.sleep(2)
|
| 14 |
return data
|
| 15 |
|
| 16 |
-
ss = extract("https://www.amazon.com/dp/B09B9TB61G?th=1")
|
| 17 |
-
print(ss)
|
|
|
|
| 1 |
import time
|
| 2 |
+
from selenium import webdriver
|
| 3 |
from selenium.webdriver import Chrome
|
| 4 |
+
from selenium.common.exceptions import TimeoutException
|
| 5 |
+
from selenium.webdriver.common.by import By
|
| 6 |
+
from selenium.webdriver.firefox.options import Options
|
| 7 |
+
from selenium.webdriver.firefox.service import Service
|
| 8 |
+
from selenium.webdriver.support import expected_conditions as EC
|
| 9 |
+
from selenium.webdriver.support.ui import WebDriverWait
|
| 10 |
+
from webdriver_manager.firefox import GeckoDriverManager
|
| 11 |
from selenium.webdriver.common.by import By
|
| 12 |
|
| 13 |
def extract(link):
|
| 14 |
url = link
|
| 15 |
+
firefoxOptions = Options()
|
| 16 |
+
firefoxOptions.add_argument("--headless")
|
| 17 |
+
service = Service(GeckoDriverManager().install())
|
| 18 |
+
driver = webdriver.Firefox(
|
| 19 |
+
options=firefoxOptions,
|
| 20 |
+
service=service,
|
| 21 |
+
)
|
| 22 |
+
driver.get(url)
|
| 23 |
+
data = driver.find_element(By.ID,"aplus_feature_div")
|
| 24 |
data = data.text
|
| 25 |
data = data.split("\n")
|
| 26 |
time.sleep(2)
|
| 27 |
return data
|
| 28 |
|
| 29 |
+
# ss = extract("https://www.amazon.com/dp/B09B9TB61G?th=1")
|
| 30 |
+
# print(ss)
|