wordpressの下载插件的历史版本的最新方法 – vulsee.com

例如：插件 https://cn.wordpress.org/plugins/baidu-submit-link/

方法一：

点击高级视图（Advanced View）：

然后拉到最下方，有个历史版本，可以下载老旧版本

方法二：

点击开发进展浏览代码：

不是所有插件有提供该界面，可以构造URL（vulsee.com）：

https://plugins.trac.wordpress.org/browser/插件名/

或者：

https://plugins.trac.wordpress.org/log/browser/插件名/

点击进去会有项目的所有文件，基本都有历史版本，可以依次下载；

为了方便，写了一个脚本，下载对应Rev编号的插件版本：

#coding:utf-8
'''
__author__=="sonic"
__website__=="http://vulsee.com"
'''
import requests
from bs4 import BeautifulSoup
import ssl
import urllib
import os
import wget
try:
    _create_unverified_https_context = ssl._create_unverified_context
except AttributeError:
    pass
else:
    ssl._create_default_https_context = _create_unverified_https_context
requests.packages.urllib3.disable_warnings()
headers = {
#需要headers
}

def getpages(file):
    startUrl = 'https://plugins.trac.wordpress.org/export/'
    resUrl = '{}{}/{}/trunk/{}'.format(startUrl,proId,proName,file)
    #print resUrl
    download(resUrl)

def download(url):
    savepath = './{}/{}/'.format(proName,proId)
    filepaths = savepath+url.split('trunk')[-1]
    fileName = url.split('trunk')[-1].split('/')[-1]
    writePathname = os.getcwd() +filepaths
    #writePath = writePathname.split('/')[0:-1]
    
    print writePathname,fileName
    writePath = writePathname.split(fileName)[0]
    
    if os.path.exists(writePath)==False:
        os.makedirs(writePath)
        wget.download(url,writePathname)
    else:
        wget.download(url,writePathname)
    
def check(path):
    url = 'https://plugins.trac.wordpress.org/browser/{}/trunk/{}?rev={}&action=inplace&range_min_secs=63679144160&range_max_secs=63726016168'.format(proName,path,proId)
    html = requests.get(url, headers=headers, verify=False).content
    #print (html)
    soup=BeautifulSoup(html,'lxml')
    files = soup.find_all("a",class_='trac-rawlink')
    for file in files:
        resfile = file.attrs["href"].split('?')[0].split('trunk')[-1]
        getpages(resfile)
    filepaths = soup.find_all("a",class_='dir')
    if len(filepaths)>0:
        for filepath in filepaths:
            respath =  filepath.attrs["href"].split('?')[0].split('trunk')[-1]
            check(respath)
            
     

def main():
    global proId,proName
    proName = 'baidu-submit-link'
    proId = 2496522 
    check('/')


if __name__ == '__main__':
    main()