selenium

selenium

from selenium.webdriver import Chrome

# 创建浏览器对象
b = Chrome()
# 打开网页
b.get('https://cd.zu.ke.com/zufang/pg2/#contentList')
# 获取网页源代码
print(b.page_source)

控制翻页

1. 找到多页规律利用循环获取多页内容

from selenium.webdriver import Chrome

# 创建浏览器对象
b = Chrome()
# 找到多页规律利用循环获取多页内容
for x in range(0, 100):
    b.get(f'https://cd.zu.ke.com/zufang/pg{x}/#contentList')
    print(b.page_source)
# dian

2. 点击翻页按钮，再刷新后获取网页源代码

# 点击翻页按钮，再刷新后获取网页源代码
b = Chrome()
b.get(f'https://cd.zu.ke.com/zufang/#contentList')
for _ in range(5):
    print(b.page_source)
    # 点击下一页按钮
    # 通过class属性名获取标签
    c = b.find_element(By.CLASS_NAME,'next')
    c.click()
    # 通过css选择器获取标签
    b.find_element(By.CSS_SELECTOR,'.next')
    # 获取标签内容为新闻的标签
    b.find_element(By.LINK_TEXT,'新闻')
    # 获取标签内容包含文闻的标签
		b.find_element(By.PARTIAL_LINK_TEXT,'闻')

1. selenium获取标签

   -关键字	-含义	说明
   By.ID	听过ID属性值获取标签
   By.CLASS_NAME	通过class属性名获取标签
   By.CSS_SELECTOR	通过css选择器获取标签
   By.LINK_TEXT	通过a标签的标签内容获取标签	只有a标签有用，必须全部匹配
   By.NAME
   By.TAG_NAME
   By.PARTIAL_LINK_TEXT	获取包含str的a标签	部分匹配
   By.XPATH

2. 输入框输入内容

   输入框对应的标签.send_keys(输入内容)

   from selenium.webdriver import Chrome
   from selenium.webdriver.common.by import By
   import time
   
   b = Chrome()
   b.get('https://www.cnki.net/')
   input_ = b.find_element(By.ID, 'txt_SearchText')
   input_.send_keys('数据分析\n')
   time.sleep(2)
   # 获取搜索结果所有标签
   with open('files/数据分析摘要.docx','a') as f:
       for _ in range(9):
           f.write(f'第{_ + 1}页\n')
           title = b.find_elements(By.CLASS_NAME, 'fz14')
           for x in range(20):
               title[x].click()
               time.sleep(1)
               b.switch_to.window(b.window_handles[-1])
               time.sleep(1)
               zhaiyao = b.find_element(By.ID, 'ChDivSummary').text
               b.close()
               f.write(f'打印第{_+1}页第{x + 1}个摘要\n')
               f.write(zhaiyao)
               b.switch_to.window(b.window_handles[0])
           next_butten = b.find_element(By.ID, 'PageNext')
           next_butten.click()
           time.sleep(3)
   
   

3. 点击标签

   标签.click()

   from selenium.webdriver import Chrome
   from selenium.webdriver.common.by import By
   import time
   
   b = Chrome()
   b.get('https://www.cnki.net/')
   input_ = b.find_element(By.ID, 'txt_SearchText')
   input_.send_keys('数据分析\n')
   time.sleep(2)
   # 获取搜索结果所有标签
   with open('files/数据分析摘要.docx','a') as f:
       for _ in range(9):
           f.write(f'第{_ + 1}页\n')
           title = b.find_elements(By.CLASS_NAME, 'fz14')
           for x in range(20):
               title[x].click()
               time.sleep(1)
               b.switch_to.window(b.window_handles[-1])
               time.sleep(1)
               zhaiyao = b.find_element(By.ID, 'ChDivSummary').text
               b.close()
               f.write(f'打印第{_+1}页第{x + 1}个摘要\n')
               f.write(zhaiyao)
               b.switch_to.window(b.window_handles[0])
           next_butten = b.find_element(By.ID, 'PageNext')
           next_butten.click()
           time.sleep(3)
   
   

4. 切换标签页

   from selenium.webdriver import Chrome
   from selenium.webdriver.common.by import By
   import time
   
   b = Chrome()
   b.get('https://www.cnki.net/')
   input_ = b.find_element(By.ID, 'txt_SearchText')
   input_.send_keys('数据分析\n')
   time.sleep(2)
   # 获取搜索结果所有标签
   with open('files/数据分析摘要.docx','a') as f:
       for _ in range(9):
           f.write(f'第{_ + 1}页\n')
           title = b.find_elements(By.CLASS_NAME, 'fz14')
           for x in range(20):
               title[x].click()
               time.sleep(1)
               b.switch_to.window(b.window_handles[-1])
               time.sleep(1)
               zhaiyao = b.find_element(By.ID, 'ChDivSummary').text
               b.close()
               f.write(f'打印第{_+1}页第{x + 1}个摘要\n')
               f.write(zhaiyao)
               b.switch_to.window(b.window_handles[0])
           next_butten = b.find_element(By.ID, 'PageNext')
           next_butten.click()
           time.sleep(3)
   
   

5. 鼠标滚动

   from selenium.webdriver import Chrome
   import time
   
   b = Chrome()
   b.get('https://www.cnki.net/')
   # 单次滚动
   b.execute_script('window.scrollBy(0,200)')
   # 多次滚动
   for x in range(8):
       b.execute_script('window.scrollBy(0,200)')
       time.sleep(2)