Rebase

parser/parser.py

@@ -68,7 +68,6 @@ def get_about_replacements() -> dict:
         count = document['body']["content"][element]["table"]["rows"]
     except (IndexError, KeyError):
         image, image_bytes = helper.find_image(document)
-        print(image)
         if not image:
             element = helper.find_with_table(document)
             if element:

parser/utils.py

@@ -32,14 +32,6 @@ self.months = {
 }
 '''
 
-headers = {
-    'user-agent':(
-        "Mozilla/5.0 (Windows NT 10.0; WOW64) "
-        "AppleWebKit/537.36 (KHTML, like Gecko) "
-        "Chrome/62.0.3202.9 Safari/537.36"
-    )
-}
-
 class Helper():
 
     def __init__(self):
@@ -199,13 +191,23 @@ class Helper():
             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 base64.b64encode(r.content).decode('utf-8')
+    
     @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"][0]:
-                    import base64
-                    return True, base64.b64encode(open("photo.png", 'rb').read()).decode('utf-8')
+                if "inlineObjectElement" in i["paragraph"]["elements"]:
+                    return True, cls.get_link_and_download(
+                        i["paragraph"]["elements"]
+                        ['inlineObjectElement']['inlineObjectId'], document)
         return False, None