自动添加至rss下载筐，方便软件自动下载

pt.py

@@ -1,5 +1,6 @@
 #!/usr/bin/python3
 # -*- coding:utf-8 -*-
+# change:添加至种子篮以自动下载
 import random
 import smtplib
 import datetime
@@ -10,6 +11,7 @@
 import re
 import requests
 from email.mime.text import MIMEText
+from urllib.parse import *
 
 #  全局变量
 global mylog
@@ -34,6 +36,15 @@ def ExtractDownloadHref( html ):  #  提取种子的超链接
     else:
         return( m.group(1) )
 
+def ExtractID(url):  # 提取种子的超链接
+    query = urlparse(url).query
+    params = dict([(k, v[0]) for k, v in parse_qs(query).items()])
+    try:
+        return params["id"]
+    except:
+        return None
+
+
 def ExtractHTML( name, s1, s2, html ):  #  配对s1+name|s2标签，提取该标签中所有内容，可处理嵌套结构
     l = len( html[0] )
     ls1 = len( s1 )
@@ -107,6 +118,7 @@ def main():
 
     mylog.debug( 'initialize .. done.' )
     torrents_found = ''         #  每个站筛出的种子累加到这里
+    # torrents_rss = []
     for pt_site in PT_Sites:    #  根据上面的数据结构循环遍历各pt站
         url = pt_site['address'] + pt_site['torrents']
         headers = pt_site['headers']
@@ -150,11 +162,13 @@ def main():
             continue
         c1 = 0; c2 = 0; c3 = 0
         content = ''  #  找到的种子存在这里
+        tids = []
         for i in range(100):  #  前100个种子
             pstr2[0] = ExtractHTML( r'', r'<tr', r'/tr>', pstr1 )  #  种子表里提取1行
             tc = ['' for j in range(8)]
             for j in range(8): tc[j] = ExtractHTML( r'', r'<td', r'/td>', pstr2 )  #  1行里提取8列
             torrenturl = pt_site['address'] + ExtractDownloadHref( tc[1] )
+            torrentid = ExtractID(torrenturl)
             for j in range(8): tc[j] = StripallTags( tc[j] )
             if ( ( tc[1] == '' ) or ( tc[3] == '' ) or ( tc[4] == '' ) or ( tc[5] == '' ) ): continue
             tc[0] = ''
@@ -180,8 +194,15 @@ def main():
                 if ( torrents_log.find( torrenturl + '\t' ) < 0 ):  #  比对是否曾经提取过该种子
                     content += tc[0] + '\n'
                     c3 += 1
+                    tids.append(torrentid)
         mylog.debug( str(c1) + ':' + str(c2) + ':' + str(c3) )
         torrents_found += content  #  各个站提取的种子累加到这个变量里
+        # torrents_rss+=[f"{pt_site['address']}myrss.php?add={torrentid}" for torrentid in tid]
+        for torrentid in tids:
+            url = f"{pt_site['address']}myrss.php?add={torrentid}"
+            headers = pt_site['headers']
+            encoding = pt_site['encoding']
+            html = GetHTML(url, headers, encoding)
     #  循环结束
     if ( torrents_found == '' ):
         mylog.info( 'found nothing new.' )