btrunghieu commited on
Commit
b2759ca
·
verified ·
1 Parent(s): f2908bd

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +5 -14
app.py CHANGED
@@ -11,7 +11,6 @@ import torch.nn as nn
11
  from transformers import AutoModel
12
  from transformers import AutoTokenizer, AutoModelForSequenceClassification
13
  import gradio as gr
14
- import brotli
15
 
16
  client = AsyncClient(
17
  # enable http2
@@ -26,25 +25,17 @@ client = AsyncClient(
26
  )
27
 
28
  def parse_comments(response: Response) -> Dict:
29
- log.debug(f"Response status code: {response.status_code}")
30
- log.debug(f"Response headers: {response.headers}")
31
-
32
  try:
33
- if 'content-encoding' in response.headers and response.headers['content-encoding'] == 'br':
34
- response_text = brotli.decompress(response.content).decode('utf-8')
35
- else:
36
- response_text = response.text
37
- data = json.loads(response_text)
38
- except json.JSONDecodeError as e:
39
- log.error(f"Failed to parse JSON response: {e}")
40
- log.error(f"Response text: {response_text[:200]}") # Log only the first 200 characters
41
  return {"comments": [], "total_comments": 0}
42
 
43
  comments_data = data.get("comments", [])
44
  total_comments = data.get("total", 0)
45
 
46
  if not comments_data:
47
- log.warning(f"No comments found in response: {response_text[:200]}")
48
  return {"comments": [], "total_comments": total_comments}
49
 
50
  parsed_comments = []
@@ -61,7 +52,7 @@ def parse_comments(response: Response) -> Dict:
61
  async def scrape_comments(post_id: int, comments_count: int = 20, max_comments: int = None) -> List[Dict]:
62
 
63
  def form_api_url(cursor: int):
64
- base_url = "https://www.tiktok.com/api/comment/list/?"
65
  params = {
66
  "aweme_id": post_id,
67
  'count': comments_count,
 
11
  from transformers import AutoModel
12
  from transformers import AutoTokenizer, AutoModelForSequenceClassification
13
  import gradio as gr
 
14
 
15
  client = AsyncClient(
16
  # enable http2
 
25
  )
26
 
27
  def parse_comments(response: Response) -> Dict:
 
 
 
28
  try:
29
+ data = json.loads(response.text)
30
+ except json.JSONDecodeError:
31
+ log.error(f"Failed to parse JSON response: {response.text}")
 
 
 
 
 
32
  return {"comments": [], "total_comments": 0}
33
 
34
  comments_data = data.get("comments", [])
35
  total_comments = data.get("total", 0)
36
 
37
  if not comments_data:
38
+ log.warning(f"No comments found in response: {response.text}")
39
  return {"comments": [], "total_comments": total_comments}
40
 
41
  parsed_comments = []
 
52
  async def scrape_comments(post_id: int, comments_count: int = 20, max_comments: int = None) -> List[Dict]:
53
 
54
  def form_api_url(cursor: int):
55
+ base_url = "https://www.tiktok.com:8080/api/comment/list/?"
56
  params = {
57
  "aweme_id": post_id,
58
  'count': comments_count,