import urllib3
import certifi
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.keys import Keys
import requests
from bs4 import BeautifulSoup
import time
import ssl
http = urllib3.PoolManager(ca_certs=certifi.where())
chrome_options = Options()
chrome_options.add_argument("--incognito")
driver = webdriver.Chrome(options=chrome_options, executable_path="D:\\python works\\driver\\chromedriver.exe")
URL= "https://physicians.wustl.edu/"
driver.get(URL)
time.sleep(5)
driver.find_element_by_link_text("Find a Doctor").click()
find_doc = driver.current_url
print(find_doc)
driver.get(find_doc)
# content = driver.page_source
# print(content)
response = http.request('GET', find_doc)
url_text = response.data #text
time.sleep(10)
count = len(driver.find_elements_by_xpath("//span[@class='entry-title-link']"))
print(count)
s = driver.find_element_by_css_selector("span[class='entry-title-link']") #firstpage click
s.click()
urls = []
provider = []
print(driver.current_url)
urls.append(driver.current_url)
name = driver.find_element_by_css_selector("h1[class='washu-ppi-name entry-title']").text
print(name)
provider.append(name)
specialization = driver.find_element_by_css_selector("ul[class='wuphys-specialties']").text
print(specialization)
location= driver.find_element_by_css_selector("a[class='wuphys-addr name']").text
print(location)
time.sleep(5)
driver.find_element_by_css_selector("a[href='https://physicians.wustl.edu/find-a-doctor/']").click()
time.sleep(10)
我有相同的跨度類名，但我需要回圈相同的類名，但 div 不同。在網址中有醫生姓名和詳細資訊點擊后我得到詳細資訊，我需要移動到下一個具有相同班級名稱的醫生
uj5u.com熱心網友回復：
我認為您正在尋找這種型別的東西（遍歷所有醫生鏈接并從那里獲取資訊）。在這里，我撰寫了一個基本操作，您可以擴展它以添加與每個醫生相關的更多資料。
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver import ActionChains
from selenium.webdriver.common.keys import Keys
import time
driver = webdriver.Chrome(options=chrome_options, executable_path="D:\\python works\\driver\\chromedriver.exe")
driver.maximize_window()
driver.get("https://physicians.wustl.edu/")
WebDriverWait(driver, 20).until(EC.visibility_of_element_located((By.LINK_TEXT, "Find a Doctor"))).click()
print(driver.current_url)
doc_cnt = WebDriverWait(driver, 10).until(EC.visibility_of_all_elements_located((By.XPATH, "//span[@class='entry-title-link']")))
print(len(doc_cnt))
doc_list=[] # to append all the doctor urls into the list for further processing, if required.
for doc in doc_cnt:
ActionChains(driver).key_down(Keys.CONTROL).click(doc).key_up(Keys.CONTROL).perform()
driver.switch_to.window(driver.window_handles[1])
doc_list.append(driver.current_url)
# ... you could include any code of yours related to each doctor here...
# After this one the tab terminates and a new doctor link would open
driver.close()
driver.switch_to.window(driver.window_handles[0])
time.sleep(1)
print(doc_list)
轉載請註明出處，本文鏈接：https://www.uj5u.com/qukuanlian/473997.html