Merge pull request #22 from steenstra/main

Add support for using filters

README.md

@@ -39,10 +39,11 @@ downloader.download(query_string, limit=100,  output_dir='dataset', adult_filter
 `adult_filter_off` : (optional, default is True) Enable of disable adult filteration.<br />
 `force_replace` : (optional, default is False) Delete folder if present and start a fresh download.<br />
 `timeout` : (optional, default is 60) timeout for connection in seconds.<br />
+`filter` : (optional, default is "") filter, choose from [line, photo, clipart, gif, transparent]<br />
 `verbose` : (optional, default is True) Enable downloaded message.<br />
 
 
-
+You can also test the programm by runnning `test.py keyword`
 
 
 ### PyPi <br />

bing_image_downloader/bing.py

@@ -12,12 +12,12 @@
 
 
 class Bing:
-    def __init__(self, query, limit, output_dir, adult, timeout,  filters='', verbose=True):
+    def __init__(self, query, limit, output_dir, adult, timeout,  filter='', verbose=True):
         self.download_count = 0
         self.query = query
         self.output_dir = output_dir
         self.adult = adult
-        self.filters = filters
+        self.filter = filter
         self.verbose = verbose
         self.seen = set()
 
@@ -37,6 +37,22 @@ def __init__(self, query, limit, output_dir, adult, timeout,  filters='', verbos
       'Accept-Language': 'en-US,en;q=0.8',
       'Connection': 'keep-alive'}
 
+
+    def get_filter(self, shorthand):
+            if shorthand == "line" or shorthand == "linedrawing":
+                return "+filterui:photo-linedrawing"
+            elif shorthand == "photo":
+                return "+filterui:photo-photo"
+            elif shorthand == "clipart":
+                return "+filterui:photo-clipart"
+            elif shorthand == "gif" or shorthand == "animatedgif":
+                return "+filterui:photo-animatedgif"
+            elif shorthand == "transparent":
+                return "+filterui:photo-transparent"
+            else:
+                return ""
+
+
     def save_image(self, link, file_path):
         request = urllib.request.Request(link, None, self.headers)
         image = urllib.request.urlopen(request, timeout=self.timeout).read()
@@ -78,7 +94,7 @@ def run(self):
             # Parse the page source and download pics
             request_url = 'https://www.bing.com/images/async?q=' + urllib.parse.quote_plus(self.query) \
                           + '&first=' + str(self.page_counter) + '&count=' + str(self.limit) \
-                          + '&adlt=' + self.adult + '&qft=' + ('' if self.filters is None else str(self.filters))
+                          + '&adlt=' + self.adult + '&qft=' + ('' if self.filter is None else self.get_filter(self.filter))
             request = urllib.request.Request(request_url, None, headers=self.headers)
             response = urllib.request.urlopen(request)
             html = response.read().decode('utf8')
@@ -97,7 +113,3 @@ def run(self):
 
             self.page_counter += 1
         print("\n\n[%] Done. Downloaded {} images.".format(self.download_count))
-        print("===============================================\n")
-        print("Please show your support here")
-        print("https://www.buymeacoffee.com/gurugaurav")
-        print("\n===============================================\n")

bing_image_downloader/downloader.py

@@ -9,7 +9,7 @@
 
 
 def download(query, limit=100, output_dir='dataset', adult_filter_off=True, 
-force_replace=False, timeout=60, verbose=True):
+force_replace=False, timeout=60, filter="", verbose=True):
 
     # engine = 'bing'
     if adult_filter_off:
@@ -34,7 +34,7 @@ def download(query, limit=100, output_dir='dataset', adult_filter_off=True,
         sys.exit(1)
 
     print("[%] Downloading Images to {}".format(str(image_dir.absolute())))
-    bing = Bing(query, limit, image_dir, adult, timeout, verbose)
+    bing = Bing(query, limit, image_dir, adult, timeout, filter, verbose)
     bing.run()
 
 

test.py

@@ -0,0 +1,22 @@
+import sys
+from bing_image_downloader import downloader
+
+query=sys.argv[1]
+
+if len(sys.argv) == 3:
+    filter=sys.argv[2]
+else:
+    filter=""
+
+
+downloader.download(
+    query,
+    limit=10,
+    output_dir="dataset",
+    adult_filter_off=True,
+    force_replace=False,
+    timeout=60,
+    filter=filter,
+    verbose=True,
+)
+