抓取微博24小时热门话题的前15个,抓取的内容请保存至txt文件中,需要抓取排行、话题和阅读数
#coding=utf-8 from selenium import webdriver import unittest from time import sleep class Weibo(unittest.TestCase): def setUp(self): self.dr = webdriver.Chrome() self.hot_list = self.get_weibo_hot_topic() self.weibo_topic = self.get_top_rank_file() def get_weibo_hot_topic(self): self.dr.get('http://weibo.com/') sleep(5) self.login('649_xxxx@qq.com','kemi_xxxx') #微博帐号密码 self.dr.get('http://d.weibo.com/100803?cfs=&Pl_Discover_Pt6Rank__5_filter=hothtlist_type%3D1#_0') sleep(5) hot_topic_list = [] i = 0 while i < 15: #rank_and_topic = self.dr.find_elements_by_css_selector('.title.W_autocut')[i].text #定位排行和话题 rank = self.dr.find_elements_by_css_selector('div.title.W_autocut>span')[i].text #定位排行 topic = self.dr.find_elements_by_css_selector('div.title.W_autocut>a.S_txt1')[i].text #定位话题 number = self.dr.find_elements_by_css_selector('.number')[i].text #定位阅读数 hot_topic_list.append([rank, topic, number]) i += 1 return hot_topic_list def get_top_rank_file(self): self.file_title = '微博24小时热门话题' self.file = open(self.file_title + '.txt', 'wb') for item in self.hot_list: separate_line = '~~~~~~~~~~~~~~~~~~~~~~~~\n' #分隔线 self.file.write(separate_line.encode('utf-8')) self.file.write((item[0]+' '+item[1]+' '+'阅读数:'+item[2]+'\n').encode('utf-8')) self.file.close() def login(self, username, password): self.dr.find_element_by_name('username').clear() self.dr.find_element_by_name('username').send_keys(username) self.dr.find_element_by_name('password').send_keys(password) self.dr.find_element_by_css_selector('.info_list.login_btn').click() def test_weibo_topic(self): pass print('抓取完毕') def tearDown(self): self.dr.quit() if __name__== '__main__': unittest.main()
网页如下:
生成txt文件如下: