我的第二十八篇博客---seleinum

标签：com   sele   slide   def   key   窗口   href   gap   int   

from selenium import webdriver

#初始化驱动
driver=webdriver.Chrome()
#请求页面
driver.get(url=‘https://www.baidu.com‘)
#找到对应标签，发送文本
driver.find_element_by_xpath("//*[@id=‘kw‘]").send_keys(‘2019‘)

#找到按钮，点击click
driver.find_element_by_xpath("//*[@id=‘su‘]").click()
#获取页面内容
content=driver.page_source
print(content)
# #解析页面

# from selenium import webdriver
# driver=webdriver.Chrome()
# driver.get(url=‘https://www.baidu.com‘)
# driver.find_element_by_xpath("//*[@id=‘kw‘]").send_keys(‘2019‘)
# driver.find_element_by_xpath("//*[@id=‘su‘]").click()
# driver.implicitly_wait(10)
# driver.find_element_by_xpath(‘//*[@class="t c-gap-bottom-small"]/a‘).click()
# content=driver.page_source
# print(content)

# from selenium import webdriver
# driver=webdriver.Chrome()
# driver.get(url=‘https://www.baidu.com‘)
# driver.find_element_by_xpath(‘//*[@id="kw"]‘).send_keys(‘2019‘)
# driver.find_element_by_xpath(‘//*[@id="su"]‘).click()
# driver.implicitly_wait(10)
# listContent=[]
# for x in range(1,10):
# content=driver.find_element_by_xpath("//*[@id=%d]/h3/a"%x).text
content=driver.find_element_by_xpath("//*[@id=%d]/h3/a"%x).get_attribute(‘href‘) #获取链接
# listContent.append(content)
# print(listContent)

# from selenium import webdriver
#
# driver=webdriver.Chrome()
# driver.get(url=‘https://movie.douban.com/‘)
# # listTitle=driver.find_elements_by_xpath("//div[@class=‘slide-page‘]/a/p")
# listTitle=driver.find_elements_by_xpath(‘//*[@id="content"]/div/div[2]/div[4]/div[3]/div/div[1]/div/div[2]/a/p‘)
# # listTitle2=[]
# # for x in listTitle:
# # listTitle2.append(x.text)
# # print(‘‘.join(listTitle2))
# for x in listTitle:
# print(x.text)

# from selenium import webdriver
# driver=webdriver.Chrome()
# driver.get(url=‘http://www.ruanyifeng.com/survivor/collapse/index.html‘)
# listTitle=driver.find_elements_by_xpath(‘/html/body/section/div/div[1]/div[2]/nav/div/aside/ul/li/ul/li/a/span[2]‘)
# for x in listTitle:
# print(x.text)

# from selenium import webdriver
# driver=webdriver.Chrome()
# driver.get(url=‘https://www.baidu.com‘)

# from selenium import webdriver
# driver=webdriver.Chrome()
# driver.get(url=‘http://www.ruanyifeng.com/survivor/collapse/index.html‘)
# #隐士等待
# driver.implicitly_wait(10)
# #点击事件
# driver.find_element_by_xpath(‘/html/body/section/div/div[1]/div[1]/article/ul/li[1]/a‘).click()
# #切换窗口
# windows=driver.window_handles
# driver.switch_to.window(windows[1])
# #获取详细页面里面的内容
# content=driver.find_element_by_xpath(‘/html/body/section/div/div[1]/div[1]/article/p[16]‘)
# print(content.text)
# #关闭当前窗口
# driver.close()

# from selenium import webdriver
# driver=webdriver.Chrome()
# driver.get(url=‘http://www.ruanyifeng.com/survivor/collapse/index.html‘)
# driver.implicitly_wait(10)
# driver.find_element_by_xpath(‘/html/body/section/div/div[1]/div[1]/article/ul/li[1]/a‘).click()
# windows=driver.window_handles
# driver.switch_to.window(windows[1])
# content=driver.find_element_by_xpath(‘/html/body/section/div/div[1]/div[1]/article/p[14]‘)
# print(content.text)
# driver.close()

# from selenium import webdriver
# driver=webdriver.Chrome()
# driver.get(url=‘http://www.ruanyifeng.com/survivor/collapse/index.html‘)
# driver.implicitly_wait(10)
# listTitle=driver.find_elements_by_xpath(‘/html/body/section/div/div[1]/div[1]/article//ul/li/a‘)
# # print(len(listTitle))
# for x in range(len(listTitle)):
# driver.find_element_by_xpath(‘/html/body/section/div/div[1]/div[1]/article//ul/li[%d]/a‘%(x+1)).click()
# windows=driver.window_handles
# driver.switch_to.window(windows[1])
# content=driver.find_element_by_xpath(‘/html/body/section/div/div[1]/div[1]/article/p[3]‘)
# print(content.text)
# driver.close()
# driver.switch_to.window(windows[0])
#
# #退出
# driver.quit()

import re
from selenium import webdriver
driver=webdriver.Chrome()
driver.get(url=‘http://www.ruanyifeng.com/survivor/collapse/index.html‘)
driver.implicitly_wait(10)
listTitle=driver.find_elements_by_xpath(‘/html/body/section/div/div[1]/div[1]/article//ul/li/a‘)
def removeTags(content):
content=re.findall("(?<=[(])[^()]+\.[^()]+(?=[)])",content)
return content

for x in range(len(listTitle)):
driver.find_element_by_xpath(‘/html/body/section/div/div[1]/div[1]/article//ul/li[%d]/a‘%(x+1)).click()
windows=driver.window_handles
driver.switch_to.window(windows[1])
content=re.findall(‘<article class="content is-size-4-desktop">(.*)</article>‘,driver.page_source,re.S)
print(removeTags(‘‘.join(content)))
driver.close()
driver.switch_to.window(windows[0])

我的第二十八篇博客---seleinum

标签：com   sele   slide   def   key   窗口   href   gap   int   

原文地址：https://www.cnblogs.com/sll-csdn/p/10926083.html