import re def getuniversity(data): rawdata = [re.findall('(.*?(?:大学|学院))', i) for i in data] return list(set([i[0] for i in rawdata if len(i) != 0])) data['University_list'] = data['Organ_list'].apply(getuniversity)什么意思
时间: 2023-11-30 08:02:08 浏览: 31
这段代码的作用是从给定的数据中提取出大学或学院的名称,并将结果存储在一个名为`University_list`的列中。
首先,导入了`re`模块,用于进行正则表达式匹配。接下来,定义了一个名为`getuniversity`的函数,该函数接受一个参数`data`。
在函数内部,首先对`data`中的每条数据应用正则表达式匹配。使用`re.findall`函数,通过正则表达式`(.*?(?:大学|学院))`来提取出满足条件的大学或学院名称。这个正则表达式表示匹配以"大学"或"学院"结尾的字符串,并尽可能少地匹配字符。
接下来,使用列表推导式对提取到的结果进行处理。首先判断每个结果列表`i`的长度是否为0,如果不为0,则说明匹配到了大学或学院的名称。然后,使用`set`函数去除重复的名称,并将结果转换为列表。
最后,通过调用DataFrame的`apply`方法,将`getuniversity`函数应用于`data['Organ_list']`这一列,并将结果存储在名为`University_list`的新列中。
总结起来,这段代码的目的是从给定的数据中提取出大学或学院的名称,并将结果保存在一个新的列中。
相关问题
用正则表达式<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>爬取猫眼电影排行:爬取猫眼电影TOP100的所有信息。网址:https://www.maoyan.com/board/4
你可以使用以下代码使用正则表达式爬取猫眼电影TOP100的所有信息:
```python
import re
import requests
url = 'https://www.maoyan.com/board/4'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36'
}
response = requests.get(url, headers=headers)
html = response.text
pattern = re.compile('<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>', re.S)
results = re.findall(pattern, html)
for result in results:
index = result[0]
image = result[1]
title = result[2]
actor = result[3].strip()[3:]
release_time = result[4].strip()[5:]
score = result[5] + result[6]
print(f'排名:{index}\n海报:{image}\n电影名:{title}\n主演:{actor}\n上映时间:{release_time}\n评分:{score}\n')
```
这段代码会发送一个GET请求到指定的URL,获取网页的HTML内容。然后使用正则表达式匹配对应的信息,并进行打印输出。注意在请求中需要添加User-Agent头部信息,以模拟浏览器访问。
import re,tkinter,requests,threading,tqdm as tt root = tkinter.Tk() root.title('在线视频解析') root.geometry('500x590+550+350') headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0'} ac = tkinter.Listbox(root, width=50, height=20, font=('黑体', 12)) ac.grid(row=2, columnspan=10, sticky="n" + "s" + "w" + "e") def sousuo(): i = b1.get() ac.delete(0, 'end') def extract_music_info(content): p = '<em>|</em>' content = re.sub(p, '', content, flags=re.S) pattern = re.compile('subject.*?href="(.*?)">(.*?)</a>', flags=re.S) return pattern.findall(content) def search_music(): url = 'https://www.hifini.com/search-' + i + '-1.htm' response = requests.get(url=url, headers=headers) return response.text def update_listbox(music_list): for music in music_list: pppp = music[1] + ":" + music[0] ac.insert('end', pppp) content = search_music() music_list = extract_music_info(content) update_listbox(music_list) def xiazzi(): def download_music(): ppp = ac.get(ac.curselection()) pp = re.search('thread.*?htm', ppp) v = pp.group() url1 = 'https://www.hifini.com/' + v response = requests.get(url=url1, headers=headers) ppp = response.text l2 = re.search('<script>.*?title:..(.*?).,.*?author:.(.*?).,.*?url:..(.*?).,', ppp, flags=re.S) p = 'https://www.hifini.com/' + l2.group(3) response = requests.get(url=p, headers=headers, stream=True) # 设置 stream=True 以启用流式下载 total_size = int(response.headers.get('Content-Length')) music_name = '{}-{}.mp3'.format(l2.group(2), l2.group(1)) progress_bar = tt.tqdm(total=total_size, unit='B', unit_scale=True) # 创建进度条 with open(music_name, 'wb') as f: for data in response.iter_content(chunk_size=1024): progress_bar.update(len(data)) # 更新进度条 f.write(data) progress_bar.close() # 关闭进度条 print(music_name) threading.Thread(target=download_music).start() a1 = tkinter.Label(root, text='音乐下载器', anchor="center", font=('黑体', 24)) a1.grid(row=0, columnspan=10, sticky="n" + "s" + "w" + "e") b1 = tkinter.Entry(root, width=35, font=('黑体', 16), ) b1.grid(row=1, column=3, padx=15) search_button = tkinter.Button(root, text='搜索', command=sousuo) search_button.grid(row=1, column=4) download_button = tkinter.Button(root, text='下载', command=xiazzi) download_button.grid(row=3, column=4) root.mainloop() 将download_button带有下载行为的按钮添加进列表,
您可以直接将download_button添加到ac(Listbox)中,然后在xiazzi函数中获取所选项,并执行下载操作。以下是修改后的代码示例:
```python
import re
import tkinter
import requests
import threading
import tqdm as tt
root = tkinter.Tk()
root.title('在线视频解析')
root.geometry('500x590+550+350')
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/115.0'}
ac = tkinter.Listbox(root, width=50, height=20, font=('黑体', 12))
ac.grid(row=2, columnspan=10, sticky="n" + "s" + "w" + "e")
def sousuo():
i = b1.get()
ac.delete(0, 'end')
def extract_music_info(content):
p = '<em>|</em>'
content = re.sub(p, '', content, flags=re.S)
pattern = re.compile('subject.*?href="(.*?)">(.*?)</a>', flags=re.S)
return pattern.findall(content)
def search_music():
url = 'https://www.hifini.com/search-' + i + '-1.htm'
response = requests.get(url=url, headers=headers)
return response.text
def update_listbox(music_list):
for music in music_list:
pppp = music[1] + ":" + music[0]
ac.insert('end', pppp)
content = search_music()
music_list = extract_music_info(content)
update_listbox(music_list)
def xiazzi():
def download_music():
ppp = ac.get(ac.curselection())
pp = re.search('thread.*?htm', ppp)
v = pp.group()
url1 = 'https://www.hifini.com/' + v
response = requests.get(url=url1, headers=headers)
ppp = response.text
l2 = re.search('<script>.*?title:..(.*?).,.*?author:.(.*?).,.*?url:..(.*?).,', ppp, flags=re.S)
p = 'https://www.hifini.com/' + l2.group(3)
response = requests.get(url=p, headers=headers, stream=True)
total_size = int(response.headers.get('Content-Length'))
music_name = '{}-{}.mp3'.format(l2.group(2), l2.group(1))
progress_bar = tt.tqdm(total=total_size, unit='B', unit_scale=True)
with open(music_name, 'wb') as f:
for data in response.iter_content(chunk_size=1024):
progress_bar.update(len(data))
f.write(data)
progress_bar.close()
print(music_name)
ac_value = ac.get(ac.curselection())
download_button = tkinter.Button(ac, text=ac_value, command=xiazzi)
ac.insert('end', download_button)
a1 = tkinter.Label(root, text='音乐下载器', anchor="center", font=('黑体', 24))
a1.grid(row=0, columnspan=10, sticky="n" + "s" + "w" + "e")
b1 = tkinter.Entry(root, width=35, font=('黑体', 16), )
b1.grid(row=1, column=3, padx=15)
search_button = tkinter.Button(root, text='搜索', command=sousuo)
search_button.grid(row=1, column=4)
root.mainloop()
```
这样,当用户选择某个音乐后,下载按钮会根据选择的音乐动态更新,点击下载按钮即可执行下载操作。