python使用selenium模块实现自动搜索百度百科词条（模拟人工搜索）

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
from bs4 import BeautifulSoupunivs &＃61; [&＃39;清华大学&＃39;, &＃39;不知道大学&＃39;, &＃39;北京大学&＃39;]
AllUnivInfolist &＃61; []browser &＃61; webdriver.Firefox() # 创建一个浏览器对象,这里还可以使用chrome等浏览器
try:browser.get(&＃39;https://baike.baidu.com/&＃39;) # 打开百科for univ in univs:browser.find_element_by_id(&＃39;query&＃39;).send_keys(univ) # 找到输入框输入字段time.sleep(3)browser.find_element_by_id(&＃39;search&＃39;).send_keys(Keys.ENTER) # 找到搜索按钮模拟点击time.sleep(3)html &＃61; browser.page_source # 获取html页面soup &＃61; BeautifulSoup(html, &＃39;html.parser&＃39;) # beautifulsoup库解析html
title &＃61; soup.find_all(&＃39;dt&＃39;, class_&＃61;"basicInfo-item name") # keynode &＃61; soup.find_all(&＃39;dd&＃39;, class_&＃61;"basicInfo-item value") # value
allunivinfo &＃61; []titlelist &＃61; []infolist &＃61; []for i in title: # 将所有dt标签内容存入列表title &＃61; i.get_text()titlelist.append(title)for i in node: # 将所有dd标签内容存入列表info &＃61; i.get_text()infolist.append(info)for i, j in zip(titlelist, infolist): # 多遍历循环&＃xff0c;zip()接受一系列可迭代对象作为参数&＃xff0c;将对象中对应的元素打包成一个个tuple&＃xff08;元组&＃xff09;&＃xff0c;然后返回由这些tuples组成的list&＃xff08;列表&＃xff09;。info &＃61; &＃39;&＃39;.join((str(i) &＃43; &＃39;:&＃39; &＃43; str(j)).split())allunivinfo.append(info)AllUnivInfolist.append(allunivinfo)# 模拟ctrl&＃43;a 操作 全选输入框内容browser.find_element_by_id(&＃39;query&＃39;).send_keys(Keys.CONTROL, &＃39;a&＃39;)time.sleep(3)# 删除输入框内容 (删除操作 模拟键盘的Backspace)browser.find_element_by_id(&＃39;query&＃39;).send_keys(Keys.BACK_SPACE)time.sleep(3)finally:browser.quit()with open("AllUnivInfo.txt", "wt", encoding&＃61;&＃39;utf8&＃39;) as out_file:for u in AllUnivInfolist:out_file.write(str(u)&＃43;&＃39;\n&＃39;)