mkbinder is ready!

1 files changed, 45 insertions, 13 deletions

diff --git a/mkbinder.py b/mkbinder.py
index 5e39eba..282c8cd 100755
--- a/mkbinder.py
+++ b/mkbinder.py
@@ -4,6 +4,9 @@ import weasyprint
 import re
 import os
 import argparse
+import pickle
+from htmldate import find_date
+from datetime import date
 
 
 # CLI arguments
@@ -22,22 +25,51 @@ for filename in os.listdir("."):
         os.mkdir(filename[:-4])
     except:
         pass
+    
+    try:
+        dates = pickle.load(open(filename[:-4] + ".pickle", 'rb'))
+    except:
+        dates = {}
 
     file = open(filename, "r")
     links = file.readlines()
     for link in links:
-        print("Downloading: " + link)
-        name = os.path.join(filename[:-4], re.sub(r'(?u)[^-\w.]', '', link[5:]) + ".pdf")
-        # name = re.sub(r'(?u)[^-\w.]', '', link[5:]) + ".pdf"
-        # print(name)
+        new_date_str = find_date(link[:-1])
+        
+        if new_date_str == None:
+            new_date = date.fromisoformat("9999-01-01")
+        else:
+            new_date = date.fromisoformat(new_date_str)
+        
         try:
-            # weasyprint seems faster?
-            if args.backend == 'pdfkit':
-                pdfkit.from_url(link, name)
-            else:
-                pdf = weasyprint.HTML(link).write_pdf()
-                open(name, 'wb').write(pdf)
+            old_date = dates[link[:-1]]
         except:
-            # Ignore exceptions
-            # Probably not a good idea
-            pass
+            old_date = date.fromisoformat("1970-01-01")
+        
+        
+        if new_date > old_date:
+            print("Downloading: " + link[:-1])
+            print("Edit date: " + str(new_date))
+            
+            name = os.path.join(filename[:-4], re.sub(r'(?u)[^-\w.]', '', link[5:]) + ".pdf")
+            # name = re.sub(r'(?u)[^-\w.]', '', link[5:]) + ".pdf"
+            # print(name)
+            try:
+                # weasyprint seems faster?
+                if args.backend == 'pdfkit':
+                    pdfkit.from_url(link, name)
+                else:
+                    pdf = weasyprint.HTML(link).write_pdf()
+                    open(name, 'wb').write(pdf)
+            except:
+                # Ignore exceptions
+                # Probably not a good idea
+                pass
+            
+            
+            if new_date != date.fromisoformat("9999-01-01"):
+                dates[link[:-1]] = new_date
+    
+    
+    pickle.dump(dates, open(filename[:-4] + ".pickle", 'wb'))
+