selenium+Chrome爬取Facebook数据

原本需求是，需要把所有的视频、赞、评论、观看量、链接、博主，爬下来，然后按观看量进行一个排序，但是因为时间原因，只完成了部分代码，基本逻辑已经清楚，待完善中。。。

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
from lxml import etree


class FacebookSpider(object):

    def __init__(self):

        print("==============================")
        print("       Geting Cookies!        ")
        print("==============================")
        # 选择浏览器
        self.browser = webdriver.Chrome(r'C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe')
        # browser.implicitly_wait(10)
        # browser.set_window_size(0,0)
        # 访问facebook网页
        self.browser.get('https://www.facebook.com/login.php?login_attempt=1&lwv=110/')
        # 输入账户密码
        self.browser.find_element_by_id('email').clear()
        self.browser.find_element_by_id('email').send_keys('你的账号')
        self.browser.find_element_by_id('pass').clear()
        self.browser.find_element_by_id('pass').send_keys('你的密码')
        # 模拟点击登录按钮，两种不同的点击方法。。。
        try:
            self.browser.find_element_by_xpath('//button[@id="loginbutton"]').send_keys(Keys.ENTER)
        except:
            self.browser.find_element_by_xpath('//input[@tabindex="4"]').send_keys(Keys.ENTER)
            # time.sleep(10)
            self.browser.find_element_by_xpath('//a[@href="https://www.facebook.com/?ref=logo"]').send_keys(Keys.ENTER)

    def send_request(seif):
        seif.browser.get("https://www.facebook.com/pg/mommonshoes/videos/?ref=page_internal/")
        soup = etree.HTML(seif.browser.page_source)
        link_list = soup.xpath("//div[@class='_3v4h _48gm _50f3 _50f7']/a/@href")
        item_list = []
        for link in link_list:
            print(link)
            item_list.append(link)
        return item_list

    def send_requestss(self, full_url):

        self.browser.get(full_url)
        time.sleep(10)
        soup = etree.HTML(self.browser.page_source)

        zan = soup.xpath("//span[@class='_1g5v']/span/text()")
        voide = soup.xpath("//span[@class='_44bh']/text()")

        print(zan)
        print(voide)

        self.browser.close()

    def main(self):
        item_list = self.send_request()
        for item in range(len(item_list)):
            full_url = "https://www.facebook.com" + item_list[item]
            print(full_url)
            self.send_requestss(full_url)


if __name__ == '__main__':
    spider = FacebookSpider()
    spider.main()