我試圖從 p 標簽中獲取文本首先轉到頁面，然后選擇語言 english并單擊advanced search，然后他們會向您顯示結果這些是頁面鏈接https://www.counselingcalifornia.com/Find-a-Therapist我正在嘗試提取p標簽的結果，他們會向我顯示錯誤
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.select import Select
from selenium import webdriver
driver = webdriver.Chrome('C:\Program Files (x86)\chromedriver.exe')
driver.maximize_window()
wait = WebDriverWait(driver, 30)
driver.get("https://www.counselingcalifornia.com/Find-a-Therapist")
wait.until(EC.frame_to_be_available_and_switch_to_it((By.CSS_SELECTOR, "iframe[id$='IFrame_htmIFrame']")))
select = Select(wait.until(EC.visibility_of_element_located((By.ID, "language_field"))))
select.select_by_value('ENG')
wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "a#searchBtn"))).click()
dunk=driver.find_elements(By.XPATH, "//div[@class='row']")
for dun in dunk:
phone=dun.find_element_by_xpath("//p[@id='phoneDiv_80863']/i[@class='fa fa-phone-square']").get_text()
print(phone)
uj5u.com熱心網友回復：
這里不需要硒。直接從url獲取請求即可。BeautifulSoup 可以獲取<p>id 屬性以"phoneDiv". 您還可以更改查詢以回傳超過 25 個。所以這里是 1-100 的串列
import requests
from bs4 import BeautifulSoup
import re
limit = 100
url = f'https://www.counselingcalifornia.com/cc/cgi-bin/utilities.dll/customlist?FIRSTNAME=~&LASTNAME=~&ZIP=&DONORCLASSSTT=&_MULTIPLE_INSURANCE=&HASPHOTOFLG=&_MULTIPLE_EMPHASIS=ÐNIC=&_MULTIPLE_LANGUAGE=ENG&QNAME=THERAPISTLIST&WMT=NONE&WNR=NONE&WHP=therapistHeader.htm&WBP=therapistList.htm&RANGE=1/{limit}&SORT=LASTNAME'
headers = {'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Mobile Safari/537.36'}
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
rows = soup.find_all('div', {'class':'row'})
for row in rows:
p = row.find('p', {'id':re.compile('^phoneDiv')})
print(p.text)
轉載請註明出處，本文鏈接：https://www.uj5u.com/caozuo/365324.html