浏览代码

added dummy mode and parsing to list

Phil 5 年之前
父节点
当前提交
28fe067a56
共有 1 个文件被更改,包括 41 次插入5 次删除
  1. 41 5
      main.py

+ 41 - 5
main.py

@@ -9,6 +9,8 @@ def main():
         print('PYrxoer Python wrapper for proxer.me')
         print('1 - Login')
         print('2 - Lesezeichen - Anime')
+        print('3 - Lesezeichen - dummy')
+        print('99 - exit')
 
         uin = input('$>: ')
         if uin == '1':
@@ -19,17 +21,34 @@ def main():
         if uin == '2':
             Lesezeichen(sess)
 
+        if uin == '3':
+            LesezeichenD()
+
+        if uin =='99':
+            exit()
+
 def Lesezeichen(sess):
     response = sess.get('https://proxer.me/ucp?s=reminder&utm_source=nav#top')
     lpars = lesezeichenParser()
-    lpars.feed(str(response.content))
-
-
-watchlist = []
-readlist = []
+    content = response.content
+    lpars.feed(str(content))
+    print(lparser.watchlist)
 
+def LesezeichenD():
+    lpars = lesezeichenParser()
+    f = open('dump.html','r')
+    content = f.readlines()
+    lpars.feed(str(content))
+    watchlist = lpars.watchlist
+    print(watchlist)
+    print('----------------------------')
+    for i in range (0,len(watchlist) - 1):
+        print(watchlist[i])
+        #print(str(i) + ' - ' + watchlist[i]['name'] + ' - ' + str(watchlist[i]['new']))
 
 class lesezeichenParser(HTMLParser):
+    watchlist = []
+    readlist = []
     inh4 = False
     inWatchlist = False
     inReadlist = False
@@ -37,7 +56,9 @@ class lesezeichenParser(HTMLParser):
     inData = False
     tdCount = 0
     inName = False
+    anime = dict()
 
+    
     def handle_starttag(self, tag, attrs):
         #headline to diff read/watchlist
         if tag == 'h4':
@@ -47,6 +68,10 @@ class lesezeichenParser(HTMLParser):
         if (self.inWatchlist or self.inReadlist) and tag == 'tr':
             self.inRow = True
             self.tdCount = 0
+            if self.inWatchlist:
+                print('new dict')
+                self.anime = dict()
+                print(self.anime)
 
         #table data for parsing info
         if self.inRow and tag == 'td':
@@ -55,7 +80,14 @@ class lesezeichenParser(HTMLParser):
 
         if self.inData and tag == 'a' and self.tdCount == 2:
             self.inName = True
+            if self.inWatchlist:
+                self.anime['link'] = attrs[2][1]
 
+        if self.inData and tag == 'img':
+            if 'online' in attrs[0]:
+                self.anime['new'] = True
+            else:
+                self.anime['new'] = False
 
     def handle_endtag(self, tag):
         if tag == 'h4' and self.inh4:
@@ -66,6 +98,9 @@ class lesezeichenParser(HTMLParser):
             self.inWatchlist = False
         if tag == 'tr' and self.inRow:
             self.inRow = False
+            if self.inWatchlist:
+                print('adding ' + str(self.anime))
+                self.watchlist.append(self.anime)
         if tag == 'td' and self.inData:
             self.inData = False
         if self.inName and tag == 'a':
@@ -82,6 +117,7 @@ class lesezeichenParser(HTMLParser):
 
         if self.inName:
             if self.inWatchlist:
+                self.anime['name'] = data
                 print(' Anime: '+data)
             if self.inReadlist:
                 print(' Manga: '+data)