python简单爬虫firefox selenium geckodriver

# coding=utf-8
 
# 1.先设置编码，utf-8可支持中英文，如上，一般放在第一行
 
# 2.注释：包括记录创建时间，创建人，项目名称。
'''
Created on 2019-11-25
@author: 
Project: python+ selenium-打开和关闭浏览器
'''
 
# 3.导入模块
from selenium import webdriver
from selenium.webdriver.firefox.options import Options

# options = Options()
# options.headless = True

class Film:
    def __init__(self, name, link):
        self.name = name
        self.link = link

def parse_news_content(url, index):
    print("parse_news_content url is : " + url + " ,index " + str(index))
    if url.startswith("http") and index < 10 :
        Fi_driver.get(url)
        elements = Fi_driver.find_elements('xpath',"//td[@width='250']/a")
        # 打印所有元素的标签名
        for element in elements:
            print("text is : " + element.text)
            href = element.get_attribute("href")
            print("href is : " + href)
            film = Film(element.text, href)
            filmList.append(film)
        
        index = index + 1
        links = Fi_driver.find_elements('xpath',"//td[@height='30']/a")
        for link in links:
            print("link text is : " + link.text)
            if link.text == "下一页" :
                href = link.get_attribute("href")
                if href is None:
                    href = ""
                if href is not None :
                    print("link href is : " + href)
                    parse_news_content(href, index)
                    break


options = webdriver.FirefoxOptions()
# options.add_argument('--headless')  # 设置为无头
options.binary_location = "C:\\develop\\firefox\\firefox.exe"
options.driver_path=  "C:\\develop\\geckodriver\\geckodriver.exe"


Fi_driver = webdriver.Firefox(options= options)

url = "https://www.dygang.tv/ys/"



res = Fi_driver.get(url)

Fi_driver.find_element('xpath','/html/head/title')

print(Fi_driver.title)






# Fi_driver.quit()

filmList = []
parse_news_content(url, 1)

for element in filmList:
    print(element.name + " , " + element.link)


Fi_driver.close()