綜合案例

　　import os

　　from selenium import webdriver

　　from selenium.webdriver.common.by import By

　　from selenium.webdriver.support import expected_conditions as EC # available since 2.26.0

　　from selenium.webdriver.support.ui import WebDriverWait # available since 2.4.0

　　from selenium.webdriver.support import expected_conditions

　　import pandas as pd

　　class MyCrawler(object):

　　def __init__(self):

　　self.path = "./data"

　　if not os.path.exists(self.path):

　　os.mkdir(self.path)

　　self.driver = webdriver.Chrome()

　　self.base_url = "http://data.house.163.com/bj/housing/trend/district/todayprice/{date:s}/{interval:s}/allDistrict/1.html?districtname={disname:s}#stoppoint"

　　self.data = None

　　def craw_page(self, date="2020.01.01-2020.12.30", interval="month", disname="全市"):

　　driver = self.driver

　　url = self.base_url.format(date=date, interval=interval, disname=disname)

　　driver.get(url)

　　try:

　　WebDriverWait(driver, 10).until(EC.presence_of_element_located((By.ID, "resultdiv_1")))

　　self.data = pd.DataFrame()

　　ct = True

　　while ct:

　　self.get_items_in_page(driver)

　　e_pages = driver.find_elements_by_xpath(

　　'//div[@class="pager_box"]/a[@class="pager_b current"]/following::a[@class="pager_b "]')

　　if len(e_pages) > 0:

　　next_page_num = e_pages[0].text

　　e_pages[0].click()

　　# 通過判斷當前頁是否為我們點擊頁面的方式來等待頁面加載完成

　　WebDriverWait(driver, 10).until(

　　expected_conditions.text_to_be_present_in_element(

　　(By.XPATH, '//a[@class="pager_b current"]'),

　　next_page_num

　　)

　　)

　　else:

　　ct = False

　　brea

　　return self.data

　　finally:

　　driver.quit()

　　def get_items_in_page(self, driver):

　　e_tr = driver.find_elements_by_xpath("http://tr[normalize-space(@class)='mBg1' or normalize-space(@class)='mBg2']")

　　temp = pd.DataFrame(e_tr, columns=['web'])

　　temp['時間'] = temp.web.apply(lambda x: x.find_element_by_class_name('wd2').text.split(' ')[0])

　　temp['套數'] = temp.web.apply(lambda x: x.find_element_by_class_name('wd5').text)

　　temp['均價'] = temp.web.apply(lambda x: x.find_element_by_class_name('wd7').text)

　　temp['去化'] = temp.web.apply(lambda x: x.find_element_by_class_name('wd14').text)

　　del temp['web']

　　self.data = pd.concat([temp, self.data], axis=0)

　　mcraw = MyCrawler()

　　data = mcraw.craw_page()

　　data= data.sort_values(by='時間')

　　print(data.to_string(index=False))