Merge pull request #102 from taoyudong/master

Fix Google Image parser
hellock · Jul 18, 2021 · 5a2e975 · 5a2e975
2 parents 7e78a9a + 2580b27
commit 5a2e975
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/icrawler/builtin/google.py b/icrawler/builtin/google.py
@@ -159,7 +159,7 @@ def parse(self, response):
             #data = meta[31][0][12][2]
             #uris = [img[1][3][0] for img in data if img[0] == 1]
 
-            uris = re.findall(r'http.*?\.(?:jpg|png|bmp)', txt)
+            uris = re.findall(r'http[^\[]*?\.(?:jpg|png|bmp)', txt)
             return [{'file_url': uri} for uri in uris]