Python爬取QQ空间好友说说并生成词云(超详细)

 1 file = ‘C:/Users/Administrator/Desktop/{}.txt‘.format(qq)
 2     driver = webdriver.Firefox()
 3     driver.maximize_window() #窗口最大化
 4 
 5     driver.get(‘https://user.qzone.qq.com/{}/311‘.format(qq))  #URL
 6     driver.implicitly_wait(10)  # 隐示等待，为了等待充分加载好网址
 7     driver.find_element_by_id(‘login_div‘)
 8     driver.switch_to_frame(‘login_frame‘) #切到输入账号密码的frame
 9     driver.find_element_by_id(‘switcher_plogin‘).click()##点击‘账号密码登录’
10     driver.find_element_by_id(‘u‘).clear() ##清空账号栏
11     driver.find_element_by_id(‘u‘).send_keys(‘你的QQ账号‘)#输入账号
12     driver.find_element_by_id(‘p‘).clear()#清空密码栏
13     driver.find_element_by_id(‘p‘).send_keys(‘你的QQ密码‘)#输入密码
14     driver.find_element_by_id(‘login_button‘).click()#点击‘登录’
15     driver.switch_to_default_content()   #跳出当前的frame，这步很关键，不写会报错的，因为你登录后还要切刀另一个frame

1     try:
2         driver.find_element_by_id(‘QM_OwnerInfo_Icon‘)#判断是否QQ空间加了权限
3         b = True
4     except:
5         b = False

1 #分4此下拉，确保能下拉到底部
2    for j in range(1, 5):
3                     driver.execute_script("window.scrollBy(0,5000)")
4                     time.sleep(2)

1                 selector = etree.HTML(driver.page_source)
2                 title = selector.xpath(‘//li/div/div/pre/text()‘)

1 driver.find_element_by_link_text(u‘下一页‘).click()

1                 for i in title:
2                     if not os.path.exists(file):
3                         print(‘创建TXT成功‘)
4 
5                     with open(file, ‘a+‘) as f:
6                         f.write(i + ‘\n\n‘)
7                         f.close()

 1 def get_wordcloud(file):
 2 
 3 
 4     f = open(file, ‘r‘, encoding=‘gbk‘).read()
 5 
 6     # 结巴分词，生成字符串，wordcloud无法直接生成正确的中文词云
 7     cut_text = " ".join(jieba.cut(f))
 8 
 9     wordcloud = WordCloud(
10         # 设置字体，不然会出现口字乱码，文字的路径是电脑的字体一般路径，可以换成别的
11         font_path="C:/Windows/Fonts/simfang.ttf",
12         # 设置了背景，宽高
13         background_color="white", width=2000, height=1380).generate(cut_text)
14 
15     plt.imshow(wordcloud, interpolation="bilinear")
16     plt.axis("off")
17     plt.show()
18#Python学习交流群：548377875