find ./ -name ??a??.*
时间: 2024-04-20 17:21:44 浏览: 22
这是一个Linux命令,用于在当前目录其子目录中查找文件名匹指定模式的文件。具体命令为:find ./ - ??a??.*。
其中,"./"表示当前目录,"-name"表示按照文件名进行匹配,"??a??.*"是文件名的模式,其中"?"表示匹配任意一个字符,"表示匹配任意多个字符。
这个命令会递归地在当前目录及子目录中查找文件名满足模式的文件,并将它们的路径。
相关问题
pattern = re.compile( '<dd>.*?board-index.*?>(.*?) </i>.*?data-src="(.*?)".*?name.*?a.*?>(.*? )</),*2star,*2(,*9) </0》,*/releasetime,*2(*I
这段代码是使用Python中的re模块来解析网页内容。其中,pattern = re.compile('<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>', re.S)是定义了一个正则表达式的模式,用于匹配特定格式的文本。
items = re.findall(pattern, html)则是使用该模式来在html中查找所有匹配的内容,并以列表的形式返回结果。
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。
相关推荐
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![docx](https://img-home.csdnimg.cn/images/20210720083331.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
用正则表达式.?board-index.?>(.?).?data-src="(.?)".?name.?a.?>(.?)
.?star.?>(.?).?releasetime.?>(.?).?integer.?>(.?).?fraction.?>(.?).?爬取猫眼电影TOP100的所有信息。网址:https://www.maoyan.com/board/4 ![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
import requests import os import time import json from tqdm import tqdm import re def taopiaopiao(): headers = { 'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Mobile Safari/537.36 Edg/113.0.1774.57' } time.sleep(0.5) url = "https://dianying.taobao.com/showList.htm?spm=a1z21.6646273.city.2.4ed46d6ekOc3wH&n_s=new&city=310100" response = requests.get(url, headers=headers) html = response.text print("网页信息已获取…") time.sleep(0.5) destinationPath = "result.txt" fd = open(destinationPath, "w+", encoding='utf-8') fd.writelines(html) end = html.find('') if end != -1: html = html[:end] #print(html) fd.close() s = '<img width="160" height="224" data-src="(.*?)" src=' + \ '.*?(.+?).*?(\d.\d)?' + \ ".*?导演:(.*?)" + ".*?主演:(.*?)" + ".*?类型:(.*?)" + \ ".*?地区:(.*?)" + ".*?语言:(.*?)" + ".*?片长:(.*?)" + \ ".*?" pattern = re.compile(s, re.S) items = re.findall(pattern, html) #print(items) destinationPath = "items.json" fd = open(destinationPath, "w+", encoding='utf-8') json.dump(items, fd) fd.close() dir_name = "./images" if not os.path.exists(dir_name): os.mkdir(dir_name) cnt = 0 for item in tqdm(items): url = item[0] file_name = str(cnt) + ".jpg" cnt += 1 response = requests.get(url, headers=headers) with open(dir_name + "/" + file_name, 'wb') as f: f.write(response.content) info = "图片文件: {0:25}{1}".format(file_name, " 成功下载...") print(info) return items if __name__ == "__main__": taopiaopiao()
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
帮我增加进度条import io import re import tkinter import requests import threading from pydub import AudioSegment 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 = '|' content = re.sub(p, '', content, flags=re.S) pattern = re.compile('subject.*?href="(.*?)">(.*?)
', 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) l3 = response.content music_name = '{}-{}.mp3'.format(l2.group(2), l2.group(1)) if l3.startswith(b'\x00\x00\x00\x20\x66\x74\x79\x70'): audio = AudioSegment.from_file(io.BytesIO(l3), format='m4a') audio.export(music_name, format='mp3') else: with open(music_name, 'wb') as f: f.write(l3) 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()![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)