erjemin/instaloader
1
0
Fork 0
Code Issues Wiki Activity

Use resumable iteration to download hashtags

Browse Source 
Closes #1457.
This commit is contained in:
Alexander Graf
2022-03-26 16:59:42 +01:00
parent d938f3e2f5
commit fbd7df2a90
3 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/cli-options.rst
View File

@@ -258,7 +258,8 @@ How to Download
- Profile posts,
- Profile IGTV posts (:option:`--igtv`),
- Profile tagged posts (:option:`--tagged`),
- Saved posts (``:saved``).
- Saved posts (``:saved``),
- Hashtags.
This feature is enabled by default for targets where it is supported;
:option:`--resume-prefix` only changes the name of the iterator files.

6
instaloader/instaloader.py
View File

@@ -1176,8 +1176,8 @@ class Instaloader:
"""Get Posts associated with a #hashtag.
.. deprecated:: 4.4
Use :meth:`Hashtag.get_posts`."""
return Hashtag.from_name(self.context, hashtag).get_posts()
Use :meth:`Hashtag.get_posts_resumable`."""
return Hashtag.from_name(self.context, hashtag).get_posts_resumable()
def download_hashtag(self, hashtag: Union[Hashtag, str],
max_count: Optional[int] = None,
@@ -1213,7 +1213,7 @@ class Instaloader:
self.download_hashtag_profilepic(hashtag)
if posts:
self.context.log("Retrieving pictures with hashtag #{}...".format(hashtag.name))
self.posts_download_loop(hashtag.get_all_posts(), target, fast_update, post_filter,
self.posts_download_loop(hashtag.get_posts_resumable(), target, fast_update, post_filter,
max_count=max_count)
if self.save_metadata:
json_filename = '{0}/{1}'.format(self.dirname_pattern.format(profile=target,

7
instaloader/structures.py
View File

@@ -1553,7 +1553,10 @@ class Hashtag:
return self._metadata("media_count")
def get_posts(self) -> Iterator[Post]:
"""Yields the recent posts associated with this hashtag."""
"""Yields the recent posts associated with this hashtag.
.. deprecated:: 4.9
Use :meth:`Hashtag.get_posts_resumable` as this method may return incorrect results (:issue:`1457`)"""
try:
self._metadata("edge_hashtag_to_media", "edges")
self._metadata("edge_hashtag_to_media", "page_info")
@@ -1575,7 +1578,7 @@ class Hashtag:
def get_all_posts(self) -> Iterator[Post]:
"""Yields all posts, i.e. all most recent posts and the top posts, in almost-chronological order."""
sorted_top_posts = iter(sorted(islice(self.get_top_posts(), 9), key=lambda p: p.date_utc, reverse=True))
other_posts = self.get_posts()
other_posts = self.get_posts_resumable()
next_top = next(sorted_top_posts, None)
next_other = next(other_posts, None)
while next_top is not None or next_other is not None: