element-ui下载到本地方法（python 或java）
鄢朝斑
最近要改造自动用例生成平台，想用element-ui改造一下前端，但是如果用webpack会比较麻烦，于是想着下载下来直接引用更方便。但是网上找了一下，有个python的要比较多C币下载，咱虽然有不少C币但这种小活干嘛不自己做一下，于是就自己写了个脚本。
至于引用本地element-ui的方法及引用后使用方法看我另一篇博文：
python版
只需要修改所要下载的版本号以及下载下来后文件所要存放的位置即可。
代码如下：
#encoding:utf-8
from bs4 import BeautifulSoup
import requests,re,os,socket
from urllib import request
#指定要下载的版本
element_ui_version = "2.13.0"
#指定文件要存放的位置
element_ui_dir = "D:/tmp"
save_ui_dir = os.path.join(element_ui_dir,"element-ui")
if not os.path.isdir(save_ui_dir):
os.makedirs(save_ui_dir)
element_ui_url = "https://unpkg.com/browse/element-ui@" + element_ui_version + "/"
headers = {
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0"
}
def get_page(url,save_dir):
print("Current Page: ",url)
response = requests.get(url,headers=headers)
soup = BeautifulSoup(str(response.content), "lxml")
tbody = soup.find("tbody")
rule_name = r'href="(.+?)"'
td_href = re.findall(rule_name,str(tbody))
dir_list = []
for href in td_href:
href_path = os.path.join(save_dir, href)
if href == "../":
pass
elif "/" in href:
os.mkdir(href_path)
print("Makedir: ",href_path.replace(save_ui_dir,""))
dir_list.append(href)
else:
file_url = url + href
abs_name = file_url.replace(element_ui_url, "")
print("Download: ", abs_name)
get_file(file_url,href_path)
for sub_dir in dir_list:
sub_url = url + sub_dir
sub_dir = os.path.join(save_dir,sub_dir)
get_page(sub_url,sub_dir)
def get_file(url,filename):
opener =request.build_opener()
opener.addheaders = [('User-agent',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0')]
request.install_opener(opener)
socket.setdefaulttimeout(30)
url = url.replace("browse/","")
count = 1
while count <= 5:
try:
request.urlretrieve(url, filename)
break
except socket.timeout:
err_info = '<Timeout> Reloading for %d time' % count
print(err_info)
count += 1
except Exception as e:
err_info = '<'+str(e)+'> Reloading for %d time' % count
print(err_info)
count += 1
if count > 5:
print("<Error> download job failed!")
else:
pass
get_page(element_ui_url,save_ui_dir)
java版
这个是网上找的，本质都是差不多的，把目录页面爬取下来，然后把href提取出来。
方法：新建一个txt改名xxx.java，然后修改版本及存放位置，最后cmd执行java xxx.java即可
代码如下：
package com.ycr;
import java.io.File;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.HttpURLConnection;
import java.net.URL;
import java.nio.charset.StandardCharsets;
import java.util.ArrayList;
public class Main {
static String fileP = "D:\\tmp\\element-ui\\";
static String urlP = "https://unpkg.com/browse/element-ui@2.13.0/";
static String urlF = "https://unpkg.com/element-ui@2.13.0/";
public static void main(String[] args){
try {
GetPage("");
} catch (Exception e) {
e.printStackTrace();
}
}
static void GetPage(String after) throws Exception {
System.out.println(urlP + after);
new File(fileP + after).mkdir();
HttpURLConnection http = (HttpURLConnection) (new URL(urlP + after)).openConnection();
http.setRequestMethod("GET");
http.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3562.0 Safari/537.36");
http.connect();
if(http.getResponseCode() == 200) {
InputStream inputStream = http.getInputStream();
byte [] buffer = new byte[1024];
ArrayList<byte []> byteList = new ArrayList<>();
ArrayList<Integer> byteLength = new ArrayList<>();
int length;
int totalLength = 0;
while( (length = inputStream.read(buffer)) != -1 ) {
byteList.add(buffer);
byteLength.add(length);
totalLength += length;
buffer = new byte[1024];
}
http.disconnect();
byte [] all;
all = new byte[totalLength];
totalLength = 0;
while(byteList.size() != 0) {
System.arraycopy(byteList.get(0), 0, all, totalLength, byteLength.get(0));
totalLength += byteLength.get(0);
byteList.remove(0);
byteLength.remove(0);
}
String content = new String(all, StandardCharsets.UTF_8);
all = null;
content = content.split("tbody")[1];
String [] us = content.split("href=\"");
for(int i = 1; i < us.length; i ++) {
String href = us[i].split("\"", 2)[0];
if(href.equals("../")) {
continue;
}
if(href.charAt(href.length() - 1) == '/') {
GetPage(after + href);
} else {
GetFile(after + href);
}
}
} else {
GetPage(after);
}
}
static void GetFile(String url) throws Exception{
System.out.println(url);
HttpURLConnection http;
http = (HttpURLConnection) (new URL(urlF + url)).openConnection();
http.setRequestMethod("GET");
http.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3562.0 Safari/537.36");
http.connect();
if(http.getResponseCode() == 200) {
InputStream inputStream = http.getInputStream();
byte [] buffer = new byte[1024];
ArrayList<byte []> byteList = new ArrayList<>();
ArrayList<Integer> byteLength = new ArrayList<>();
int length;
int totalLength = 0;
while( (length = inputStream.read(buffer)) != -1 ) {
byteList.add(buffer);
byteLength.add(length);
totalLength += length;
buffer = new byte[1024];
}
http.disconnect();
byte [] all;
all = new byte[totalLength];
totalLength = 0;
while(byteList.size() != 0) {
System.arraycopy(byteList.get(0), 0, all, totalLength, byteLength.get(0));
totalLength += byteLength.get(0);
byteList.remove(0);
byteLength.remove(0);
}
File f = new File(fileP + url.replaceAll("/", "\\\\"));
f.createNewFile();
FileOutputStream fos = new FileOutputStream(f, false);
fos.write(all);
fos.flush();
fos.close();
} else {
GetFile(url);
}
}
}
不过，因为这个网站服务器是位于美国的，所以速度会比较慢。而且好像有防爬虫机制，如果频繁重复下载会有一定的限制，不过很快的就解除就是了。
类似资料：