backup/google_parser/parser/parser.py

@@ -67,11 +67,13 @@ def get_about_replacements() -> dict:
     try:
         count = document['body']["content"][element]["table"]["rows"]
     except (IndexError, KeyError):
-        element = helper.find_with_table(document)
-        if element:
-            count = document['body']["content"][element]["table"]["rows"]
-        else:
-            info = helper.find_with_text(document)
+        image, image_bytes = helper.find_image(document)
+        if not image:
+            element = helper.find_with_table(document)
+            if element:
+                count = document['body']["content"][element]["table"]["rows"]
+            else:
+                info = helper.find_with_text(document)
 
     date = helper.get_date(document)
 
@@ -101,6 +103,13 @@ def get_about_replacements() -> dict:
                 )
             )
 
+    if image:
+        return {
+            "image": image,
+            'date': date if type(date) != type(False) else "Error" ,
+            'data': {"all": image_bytes},
+            'another_teacher': another_teacher,
+        }
     return {
         'date': date if type(date) != type(False) else "Error" ,
         'data': dict(info),

backup/google_parser/parser/utils.py

@@ -2,6 +2,8 @@ import os
 import datetime
 from datetime import datetime as dt
 
+import requests
+
 from load import config
 
 
@@ -186,3 +188,25 @@ class Helper():
                             return doc
 
             element += 1
+            
+        
+    @classmethod
+    def get_link_and_download(cls, id_doc, document):
+        if "inlineObjects" in document:
+            if id_doc in document['inlineObjects']:
+                link = (document
+                    ['inlineObjects'][id_doc]['inlineObjectProperties']
+                    ['embeddedObject']['imageProperties']['contentUri'])
+                r = requests.get(link, stream=True)
+                return r.raw
+    
+    @classmethod
+    def find_image(cls, document):
+        for i in document['body']["content"]:
+            if ("paragraph" in i) and ("elements" in i["paragraph"]):
+                if "inlineObjectElement" in i["paragraph"]["elements"]:
+                    return True, cls.get_link_and_download(
+                        i["paragraph"]["elements"]
+                        ['inlineObjectElement']['inlineObjectId'], document)
+        return False, None
+