Обработка "неприводимых к латинице и кириллице" имен авторов с возможностью ручного...

[openlib.git] / get_flibusta.py

diff --git a/get_flibusta.py b/get_flibusta.py
index 13768c47930a9be4b4477d29c74460088a45f8da..64098473bba78122d023f2f6ec2aff990651db9b 100755 (executable)
--- a/get_flibusta.py
+++ b/get_flibusta.py
@@ -12,7 +12,7 @@ os.environ['no_proxy']='localhost,127.0.0.1'
 proxies = {'http': 'http://localhost:3128'}
 
 
 proxies = {'http': 'http://localhost:3128'}
 
 

-for host in ['flibustahezeous3.onion','flibusta.i2p','flibusta.net']:
+for host in ['flibusta.lib','flibustahezeous3.onion','flibusta.i2p']:

 
   try:
     print "Trying %s" % (host)
 
   try:
     print "Trying %s" % (host)


@@ -20,13 +20,13 @@ for host in ['flibustahezeous3.onion','flibusta.i2p','flibusta.net']:
     html = BeautifulSoup(html_page)
 
     os_command = "wget -c -q -P \"%s\" http://%s/daily/%s" % (db.upload_files,host,'%s')
     html = BeautifulSoup(html_page)
 
     os_command = "wget -c -q -P \"%s\" http://%s/daily/%s" % (db.upload_files,host,'%s')

-    print os_command   

     matched = False 
 
     for link in html.findAll('a'):
       file = link.get("href")
       print file
       if pattern.match(file):
     matched = False 
 
     for link in html.findAll('a'):
       file = link.get("href")
       print file
       if pattern.match(file):

+        print "Pattern matched"

         matched = True
         if not db.TestArchive(file):
           print "Processing %s" % file
         matched = True
         if not db.TestArchive(file):
           print "Processing %s" % file