刮谷歌地圖提供這些錯誤無效引數：'URL'必須是一個字串

當我運行我的代碼時，他們會向我提供這些錯誤 selenium.common.exceptions.InvalidArgumentException: Message: invalid argument: 'URL' must be a string，當他們去抓取第二個標題時，他們會抓取第一個標題，他們會向我提供錯誤，即您的 URL 是一個字串，這些是頁面鏈接https://www.google。 com/maps/search/uk dentist/@31.5688259,74.2388013,12z/data=!3m1!4b1

import time
from selenium import webdriver
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from webdriver_manager.chrome import ChromeDriverManager

options = webdriver.ChromeOptions()

# options.add_argument("--headless")
options.add_argument("--no-sandbox")
options.add_argument("--disable-gpu")
options.add_argument("--window-size=1920x1080")
options.add_argument("--disable-extensions")

chrome_driver = webdriver.Chrome(
    service=Service(ChromeDriverManager().install()),
    options=options
)


def supplyvan_scraper():
    with chrome_driver as driver:
        driver.implicitly_wait(15)
        URL = 'https://www.google.com/maps/search/dentist uk/@31.5688259,74.2388013,12z/data=!3m1!4b1'
        driver.get(URL)
        time.sleep(3)
        page_links = [element.get_attribute('href') for element in
                      driver.find_elements(By.XPATH, "//div[@class='Nv2PK Q2HXcd THOPZb']//a")]

        # visit all the links
        for link in page_links:
            driver.get(link)
            time.sleep(2)
            title = driver.find_element(By.XPATH, "//h1[@class='DUwDvf fontHeadlineLarge']//span").text

            # parse title for all the links
            print(title)
            # driver.back()
            time.sleep(2)

        time.sleep(2)
        driver.quit()


supplyvan_scraper()

uj5u.com熱心網友回復：

就我而言，除了一切正常之外，它在標題元素選擇方面有點麻煩。

import time
from selenium import webdriver
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from webdriver_manager.chrome import ChromeDriverManager
import pandas as pd
options = webdriver.ChromeOptions()

# options.add_argument("--headless")
options.add_argument("--no-sandbox")
options.add_argument("--disable-gpu")
options.add_argument("--window-size=1920x1080")
options.add_argument("--disable-extensions")

chrome_driver = webdriver.Chrome(service=Service(ChromeDriverManager().install()),options=options)
data=[]
def supplyvan_scraper():
    with chrome_driver as driver:
        driver.implicitly_wait(15)
        URL = 'https://www.google.com/maps/search/dentist uk/@31.5688259,74.2388013,12z/data=!3m1!4b1'
        driver.get(URL)
        time.sleep(3)
        page_links = [element.get_attribute('href') for element in driver.find_elements(By.XPATH, '//*[@]')]

        # visit all the links
        for link in page_links:
            print(link)
            driver.get(link)
            time.sleep(2)
            title = driver.find_element(By.XPATH, '//h1[@]/span[1]').text
            data.append(title)
            # parse title for all the links
            #print(title)
            # driver.back()
            time.sleep(2)

        # time.sleep(2)
        # driver.quit()


supplyvan_scraper()

df = pd.DataFrame(data,columns=['title'])

print(df)

輸出：

                                  title
0                          YOR Dental at MediaCityUK
1               Blossom Dental Care & Implant Studio
2                         Blackbrook Dental Practice
3                          Greenwich Dental Practice
4                                        NHS Dentist
5                               London Dental Centre
6                          New Cross Dental Practice
7                                       Dental Works
8                             Huntingdon Dental Care
9  Advance Dental Care - Private & NHS | Invisali...

標籤：Python 硒 网页抓取

上一篇：無法在python中獲取bs4表內容

下一篇：Scarpy無法抓取簡單的網站，因為它提供了空資料