pacxxxxxxx

pip install selenium

pip install requsets

pip install BeautifulSoup4

pip install bs4

 

 

11111#lxml爬取网页内容

import requests

ua="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"

html=requests.get('https://yjsy.hunnu.edu.cn/zsks/sszk1.htm',headers={'User-Agent':ua})

html.encoding='utf-8'

#print(html.text)文本都在html.test里面

 

#获取节点

xpath="//a[@target='_blank']"

from lxml import etree

page =etree.HTML(html.text)

#xpath方法

result =page.xpath(xpath)

 

for i in result:

    print(i.text)

 

 

print()

print("符合条件的结果有")

for i in result:

   if '湖南' in i.text and '录取' in i.text:

     print(i.text)   

 

 

2222# selenium 方法截图

from selenium import webdriver

driver =webdriver.PhantomJS()

driver.get('https://www.baidu.com/')

driver.find_element_by_id('kw').send_keys(u"湘潭理工学院")

driver.find_element_by_id('su').click()

import time

time.sleep(5)

driver.save_screenshot('b1.png')

 

 

3333#selenium方法的actionchains点击网页

from selenium import webdriver

#不关闭浏览器

 

options= webdriver.EdgeOptions()

options.add_experimental_option('detach',True)

#Chrome 谷歌 ChromiumEdge新E浏览器Edge老版

driver = webdriver.ChromiumEdge(options=options)

driver.get('https://yjsy.hunnu.edu.cn/')

#得到一个不关闭的浏览器

 

from selenium.webdriver.common.by import By

import time

 

xpath1="//ul[@class='menu']/li[4]/a"

xpath2="//ul[@class='menu']/li[4]/ul/li[2]/a"

 

b1=driver.find_element(By.XPATH,xpath1)

b2=driver.find_element(By.XPATH,xpath2)

 

from selenium.webdriver import ActionChains

ActionChains(driver).move_to_element(b1).perform()

time.sleep(3)

ActionChains(driver).move_to_element(b2).perform()

time.sleep(3)

ActionChains(driver).move_to_element(b2).click().perform()

 

 

4444#selenium方法By.id点击网页

from selenium import webdriver

#不关闭浏览器

 

options= webdriver.EdgeOptions()

options.add_experimental_option('detach',True)

#Chrome 谷歌 ChromiumEdge新E浏览器

driver = webdriver.ChromiumEdge(options=options)

driver.get('http:/www.baidu.com')

#得到一个不关闭的浏览器

 

from selenium.webdriver.common.by import By

import time

driver.find_element(By.ID,'kw').send_keys('湖南师范大学研究生院')

time.sleep(3)

#click点击出现  

driver.find_element(By.ID,'su').click()

 

5555#beautifulsoup爬取网页

import requests

ua="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"

html=requests.get('https://yjsy.hunnu.edu.cn/zsks/sszk1.htm',headers={'User-Agent':ua})

html.encoding='utf-8'

 

 

#引入beautifulsoup

from bs4 import BeautifulSoup

soup = BeautifulSoup(html.text, 'lxml')

#用findall方法找符合条件的节点

result = soup.find_all('a',target='_blank')

#print(result)

 

for i in result:

    print(i.text)

 

print()

print("符合结果的有：")

for i in result:

    if '大学' in i.text and '2024' in i.text:

        print(i.text)

 

6666#selenium方法得到网页和bs4爬取网页内容

from selenium import webdriver

url='https://www.bilibili.com/video/BV1iN4y1a7KJ'options=webdriver.ChromeOptions()

options.add_experimental_option('detach', True)

driver=webdriver.Chrome(options=options)

driver.get(url)

import time

time.sleep(5)

html = driver.page_source

from bs4 import BeautifulSoup

soup = BeautifulSoup(html, 'lxml')

title = soup.find('h1', class_="video-title")

count = soup.find('span', class_="view item")

dm = soup.find('span', class_="dm item")

datetime = soup.find('span', class_="pubdate-text")

comments = soup.find_all('div', class_="content-warp")

comments_text = []

for comment in comments:

       name = comment.find('div', class_="user-info").text

text = comment.find('span', class_="reply-content").text

comments_text.append({

'name': name,

'text': text })

# 输出结果

print(f"标题：{title.text}，播放量：{count.text.strip()}，弹幕数：{dm.text.strip()}")

for comment in comments_text: print(f"评论：\nID:{comment['name']}，评论内容：{comment['text']}")

driver.close()