README.md aktualisiert

README.md

@@ -0,0 +1,18 @@
+# Scraperchan
+A simple program to scrape 4Chan Threads for Images and Videos
+
+Install dependencies:
+
+```shell
+git clone https://git.protron.dev/Doc/scraperchan.git
+
+cd scraperchan
+
+pip install -r requirements.txt
+```
+
+Usage:
+
+```shell
+python scraperchan -u <Thread URL> -o <Local target directory>
+```

readme.md

@@ -1,9 +0,0 @@
-# Scraperchan
-A simple program to scrape 4Chan Threads for Images (videos aren't supporter yet)
-
-usage:
-
-```shell
-python scraperchan -u <Thread URL> -o <Local target directory>
-
-```

requirements.txt

@@ -1,4 +1,3 @@
 requests
 argparse
 Pillow
-ffmpeg-python

scraperchan.py

@@ -1,4 +1,4 @@
-import requests, json, time, argparse, sys, os, ffmpeg
+import requests, json, time, argparse, sys, os
 from PIL import Image
 from io import BytesIO
 
@@ -12,7 +12,7 @@ args = parser.parse_args()
 
 r = requests.get(args.u + ".json")
 
-print("Got main request")
+print("Got main request from " + args.u + ".json" )
 
 rjson = r.json()
 
@@ -22,7 +22,7 @@ for i in rjson['posts']:
     if "ext" in i:
         ir = requests.get("https://i.4cdn.org/" + board + "/"  + str(i['tim']) + i['ext'])
         
-        print("Got post request")
+        print("Got post request for: " + board + "/"  + str(i['tim']) + i['ext'])
 
         bstream = BytesIO(ir.content)
 
@@ -30,23 +30,24 @@ for i in rjson['posts']:
             ir = requests.get("https://i.4cdn.org/" + board + "/"  + str(i['tim']) + i['ext'])
             im = Image.open(bstream)
             print("Converted bytes to image")
-            im.save(args.o + "/" + str(i['tim']) + i['ext'])
+            im.save(args.o + "/" + board + "-" + str(i['tim']) + i['ext'])
-            print("Saved image")
+            print("Saved image: " + board + "-" + str(i['tim']) + i['ext'])
         except KeyboardInterrupt:
             print('Closing')
             try:
                 sys.exit(130)
             except SystemExit:
                 os._exit(130)
-        except:
+        except: 
-            print("Cant convert data to image maybe not an image format")
-            print("NO:" + str(i['no']))
-            """
             try:
-                ffmpeg.input(bstream).output(args.o + "/" + str(i['tim']) + ".mp4").run()
+                with open(args.o + "/" + board + str(i['tim']) + i['ext'], 'wb') as f:
-                print("Saved video")
+                    f.write(bstream.getbuffer())
-            except:
+                f.close()
-                print("Cant convert to Video")         
+                print("Saved video: " + board + "-" + str(i['tim']) + i['ext'])
-            """
+            except Exception as err:
-
+                print("Cant convert data to image or video maybe not an image or video format")
+                print("NO: " + str(i['no']))
+                print(err)         
+        
+        time.sleep(1)
 print("Done!!")