Day4 selenium滚动和常见fanpa
1. zhi网页面数据分析
'''
Author:KathAmy
Date:2022/8/16 9:15
键盘敲烂,共同进步!
'''
from selenium.webdriver import Chrome
from time import sleep
from bs4 import BeautifulSoup
def analysis_data(html: str):
soup = BeautifulSoup(html, 'lxml')
title = soup.select_one('.wx-tit>h1')
if title:
title = title.text
author = soup.select_one('#authorpart a')
if author:
author = author.text
organization = soup.select_one('.wx-tit>h3:nth-child(3) a')
if organization:
organization = organization.text
print(title)
print(author)
print(organization)
print('-----------------------------------华丽的分割线-----------------------------------')
def get_paper(key_word='数据分析'):
global b
b = Chrome()
b.get('https://www.cnki.net/')
b.find_element_by_id('txt_SearchText').send_keys(f'{
key_word}\n')
sleep(1)
for x in range(5):
all_a = b.find_elements_by_css_selector('.result-table-list .name>a'