erjemin/instaloader
erjemin/instaloader
1
0
Fork 0
Code Issues Wiki Activity

Fix bugs in Instaloader.update_comments()

Browse Source 
- Cast id and created_at from JSON to int to be compatible with comments JSON
  files from Instaloader 3.3,
- Do not fail if comment JSON files are empty,
- Close file descriptors of comment JSON files when reading,
- Do no create empty comment JSON files if generating content fails.

Closes #114.
This commit is contained in:
Alexander Graf 2018-05-08 17:39:00 +02:00
parent 5204990db9
commit b3df5a5f07
1 changed files with 14 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
instaloader/instaloader.py
View File

@ -178,27 +178,28 @@ class Instaloader:
def update_comments(self, filename: str, post: Post) -> None: def update_comments(self, filename: str, post: Post) -> None:
def _postcomment_asdict(comment): def _postcomment_asdict(comment):
return {'id': comment.id, return {'id': comment.id,
'created_at': comment.created_at_utc.replace(tzinfo=timezone.utc).timestamp(), 'created_at': int(comment.created_at_utc.replace(tzinfo=timezone.utc).timestamp()),
'text': comment.text, 'text': comment.text,
'owner': comment.owner._asdict()} 'owner': comment.owner._asdict()}
filename += '_comments.json' filename += '_comments.json'
try: try:
comments = json.load(open(filename)) with open(filename) as fp:
except FileNotFoundError: comments = json.load(fp)
except (FileNotFoundError, json.decoder.JSONDecodeError):
comments = list() comments = list()
comments.extend(_postcomment_asdict(comment) for comment in post.get_comments()) comments.extend(_postcomment_asdict(comment) for comment in post.get_comments())
if comments: if comments:
comments_list = sorted(sorted(list(comments), key=lambda t: int(t['id'])),
key=lambda t: int(t['created_at']), reverse=True)
unique_comments_list = [comments_list[0]]
#for comment in comments_list:
# if unique_comments_list[-1]['id'] != comment['id']:
# unique_comments_list.append(comment)
#file.write(json.dumps(unique_comments_list, indent=4))
for x, y in zip(comments_list[:-1], comments_list[1:]):
if x['id'] != y['id']:
unique_comments_list.append(y)
with open(filename, 'w') as file: with open(filename, 'w') as file:
comments_list = sorted(sorted(list(comments), key=lambda t: t['id']),
key=lambda t: t['created_at'], reverse=True)
unique_comments_list = [comments_list[0]]
#for comment in comments_list:
# if unique_comments_list[-1]['id'] != comment['id']:
# unique_comments_list.append(comment)
#file.write(json.dumps(unique_comments_list, indent=4))
for x, y in zip(comments_list[:-1], comments_list[1:]):
if x['id'] != y['id']:
unique_comments_list.append(y)
file.write(json.dumps(unique_comments_list, indent=4)) file.write(json.dumps(unique_comments_list, indent=4))
self.context.log('comments', end=' ', flush=True) self.context.log('comments', end=' ', flush=True)