Spaces:
Sleeping
Sleeping
Update main.py
Browse files
main.py
CHANGED
@@ -62,124 +62,124 @@ async def test_google(code:str):
|
|
62 |
access_token = response.json().get("access_token")
|
63 |
print("printing access token , yo yo test")
|
64 |
print(access_token)
|
65 |
-
|
66 |
-
# if not access_token:
|
67 |
-
# raise HTTPException(status_code=400, detail="Authorization code not provided")
|
68 |
-
print("Entered this function, for testing purposes")
|
69 |
-
brand_name = "louis vuitton"
|
70 |
-
|
71 |
-
user_info = requests.get("https://www.googleapis.com/oauth2/v1/userinfo", headers={"Authorization": f"Bearer {access_token}"})
|
72 |
-
page_token = None
|
73 |
-
messages = []
|
74 |
-
# user_query = f"subject:((receipt {brand_name}) OR (receipts {brand_name}) OR (reçu {brand_name}) OR (reçus {brand_name}) OR (Quittung {brand_name}) OR (Quittungen {brand_name}) OR (aankoopbon {brand_name}) OR (aankoopbonnen {brand_name}) OR (recibo {brand_name}) OR (recibos {brand_name}) OR (ricevuta {brand_name}) OR (ricevute {brand_name}) OR (ontvangstbewijs {brand_name}) OR (ontvangstbewijzen {brand_name})) has:attachment"
|
75 |
-
# user_query = f"{brand_name} label:^smartlabel_receipt"
|
76 |
-
user_query = f"(label:^smartlabel_receipt OR (subject:your AND subject:order) OR subject:receipts OR subject:receipt OR subject:invoice OR subject:invoice)) AND subject:amazon"
|
77 |
-
# user_query = """("invoice" OR (("tracking" OR "track") AND ("delivery" OR "package"))) OR (subject:order OR subject:receipt OR subject:receipts OR subject:invoice OR subject:invoice)"""
|
78 |
-
while True:
|
79 |
-
|
80 |
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
|
85 |
-
|
86 |
-
|
87 |
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
unique_thread_ids = set()
|
99 |
-
|
100 |
-
filtered_data_list = []
|
101 |
-
|
102 |
-
for entry in messages:
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
attachments = []
|
109 |
-
attachment_no = 0
|
110 |
-
data_new = {}
|
111 |
-
for i,message in enumerate(messages) :
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
|
147 |
-
|
148 |
-
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
|
159 |
-
|
160 |
-
|
161 |
-
|
162 |
|
163 |
|
164 |
-
|
165 |
-
|
166 |
-
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
return {"attachment_count":attachment_no,"attachment_content":data_new}
|
183 |
|
184 |
|
185 |
def extract_text_and_links(html_content):
|
|
|
62 |
access_token = response.json().get("access_token")
|
63 |
print("printing access token , yo yo test")
|
64 |
print(access_token)
|
65 |
+
return {"access_token":access_token}
|
66 |
+
# # if not access_token:
|
67 |
+
# # raise HTTPException(status_code=400, detail="Authorization code not provided")
|
68 |
+
# print("Entered this function, for testing purposes")
|
69 |
+
# brand_name = "louis vuitton"
|
70 |
+
|
71 |
+
# user_info = requests.get("https://www.googleapis.com/oauth2/v1/userinfo", headers={"Authorization": f"Bearer {access_token}"})
|
72 |
+
# page_token = None
|
73 |
+
# messages = []
|
74 |
+
# # user_query = f"subject:((receipt {brand_name}) OR (receipts {brand_name}) OR (reçu {brand_name}) OR (reçus {brand_name}) OR (Quittung {brand_name}) OR (Quittungen {brand_name}) OR (aankoopbon {brand_name}) OR (aankoopbonnen {brand_name}) OR (recibo {brand_name}) OR (recibos {brand_name}) OR (ricevuta {brand_name}) OR (ricevute {brand_name}) OR (ontvangstbewijs {brand_name}) OR (ontvangstbewijzen {brand_name})) has:attachment"
|
75 |
+
# # user_query = f"{brand_name} label:^smartlabel_receipt"
|
76 |
+
# user_query = f"(label:^smartlabel_receipt OR (subject:your AND subject:order) OR subject:receipts OR subject:receipt OR subject:invoice OR subject:invoice)) AND subject:amazon"
|
77 |
+
# # user_query = """("invoice" OR (("tracking" OR "track") AND ("delivery" OR "package"))) OR (subject:order OR subject:receipt OR subject:receipts OR subject:invoice OR subject:invoice)"""
|
78 |
+
# while True:
|
79 |
+
# # Construct Gmail API request with pageToken
|
80 |
|
81 |
+
# gmail_url = f"https://www.googleapis.com/gmail/v1/users/me/messages?q={user_query}"
|
82 |
+
# if page_token:
|
83 |
+
# gmail_url += f"&pageToken={page_token}"
|
84 |
|
85 |
+
# gmail_response = requests.get(gmail_url, headers={"Authorization": f"Bearer {access_token}"})
|
86 |
+
# gmail_data = gmail_response.json()
|
87 |
|
88 |
+
# # Check if there are messages in the response
|
89 |
+
# if "messages" in gmail_data:
|
90 |
+
# messages.extend(gmail_data["messages"])
|
91 |
+
|
92 |
+
# # Check if there are more pages
|
93 |
+
# if "nextPageToken" in gmail_data:
|
94 |
+
# page_token = gmail_data["nextPageToken"]
|
95 |
+
# else:
|
96 |
+
# break # No more pages, exit the loop
|
97 |
+
|
98 |
+
# unique_thread_ids = set()
|
99 |
+
|
100 |
+
# filtered_data_list = []
|
101 |
+
|
102 |
+
# for entry in messages:
|
103 |
+
# thread_id = entry['threadId']
|
104 |
+
# if thread_id not in unique_thread_ids:
|
105 |
+
# unique_thread_ids.add(thread_id)
|
106 |
+
# filtered_data_list.append(entry)
|
107 |
+
|
108 |
+
# attachments = []
|
109 |
+
# attachment_no = 0
|
110 |
+
# data_new = {}
|
111 |
+
# for i,message in enumerate(messages) :
|
112 |
+
# # print(i)
|
113 |
+
# # print(message)
|
114 |
+
|
115 |
+
# if message:
|
116 |
+
# message_id = message.get("id")
|
117 |
+
# print(message_id)
|
118 |
+
# if message_id:
|
119 |
+
# message_url = f"https://www.googleapis.com/gmail/v1/users/me/messages/{message_id}"
|
120 |
+
# message_response = requests.get(message_url, headers={"Authorization": f"Bearer {access_token}"})
|
121 |
+
# message_data = message_response.json()
|
122 |
+
# print("printing message_data response json")
|
123 |
+
# print(message_data)
|
124 |
+
# print("Finished printing message_data response json")
|
125 |
+
|
126 |
+
# subject = ''
|
127 |
+
# body = ''
|
128 |
+
# print("printing body")
|
129 |
+
# print(message_data['snippet'])
|
130 |
+
# if 'payload' in message_data and 'headers' in message_data['payload']:
|
131 |
+
# headers = message_data['payload']['headers']
|
132 |
+
# for header in headers:
|
133 |
+
# if header['name'] == 'Subject':
|
134 |
+
# subject = header['value']
|
135 |
|
136 |
+
# if 'parts' in message_data['payload']:
|
137 |
+
# parts = message_data['payload']['parts']
|
138 |
+
# print("printing parts")
|
139 |
+
# print(parts)
|
140 |
+
|
141 |
+
# for part in parts:
|
142 |
+
# if part['mimeType'] == 'text/plain' or part['mimeType'] == 'text/html':
|
143 |
+
# body_data = part['body']['data']
|
144 |
+
# print("printing body data")
|
145 |
+
# print(body_data)
|
146 |
+
# body = base64.urlsafe_b64decode(body_data)
|
147 |
+
# print("Subject:", subject)
|
148 |
+
# if body:
|
149 |
+
# text,links=extract_text_and_links(body)
|
150 |
+
# if text:
|
151 |
+
# print("Printing extracted Text: ")
|
152 |
+
# print(text)
|
153 |
+
# else:
|
154 |
+
# print("No text found or there was some error parsing.")
|
155 |
+
|
156 |
+
# if links:
|
157 |
+
# print("\nLinks:")
|
158 |
+
# for link_text, link_url in links:
|
159 |
+
# print(f"{link_text}: {link_url}")
|
160 |
+
# else:
|
161 |
+
# print("No links found or there was some error in parsing or maybe don't use for loop.")
|
162 |
|
163 |
|
164 |
+
# # Check for parts in the message payload
|
165 |
+
# if "payload" in message_data and "parts" in message_data["payload"]:
|
166 |
+
# for part in message_data["payload"]["parts"]:
|
167 |
+
# if "body" in part and "attachmentId" in part["body"]:
|
168 |
+
# attachment_id = part["body"]["attachmentId"]
|
169 |
+
# attachment_url = f"https://www.googleapis.com/gmail/v1/users/me/messages/{message_id}/attachments/{attachment_id}"
|
170 |
+
# attachment_response = requests.get(attachment_url, headers={"Authorization": f"Bearer {access_token}"})
|
171 |
+
# attachment_data = attachment_response.json()
|
172 |
+
# data = attachment_data.get("data")
|
173 |
+
# filename = part.get("filename", "untitled.txt")
|
174 |
+
|
175 |
+
# if data:
|
176 |
+
# data_new[filename]=data[:10]
|
177 |
+
# # attachment_content = base64.urlsafe_b64decode(data)
|
178 |
+
# # extracted_text = await extract_text_from_attachment(filename, attachment_content)
|
179 |
+
|
180 |
+
# attachment_no+=1
|
181 |
+
|
182 |
+
# return {"attachment_count":attachment_no,"attachment_content":data_new}
|
183 |
|
184 |
|
185 |
def extract_text_and_links(html_content):
|