1
0
mirror of https://github.com/instaloader/instaloader.git synced 2024-11-20 17:22:31 +01:00

Include top posts in download_hashtag()

This commit is contained in:
Alexander Graf 2020-04-19 12:21:27 +02:00
parent b98e9941ae
commit 0e13c73b62
3 changed files with 27 additions and 2 deletions

View File

@ -926,7 +926,7 @@ 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_posts(), target, fast_update, post_filter,
self.posts_download_loop(hashtag.get_all_posts(), target, fast_update, post_filter,
max_count=max_count)
if self.save_metadata:
json_filename = '{0}/{1}'.format(self.dirname_pattern.format(profile=target,

View File

@ -1267,6 +1267,31 @@ class Hashtag:
conn = data["edge_hashtag_to_media"]
yield from (Post(self._context, edge["node"]) for edge in conn["edges"])
def get_all_posts(self) -> Iterator[Post]:
"""Yields all posts, i.e. all most recent posts and the top posts, in chronological order."""
sorted_top_posts = iter(sorted(self.get_top_posts(), key=lambda p: p.date_utc, reverse=True))
other_posts = self.get_posts()
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:
if next_other is None:
yield from sorted_top_posts
break
if next_top is None:
yield from other_posts
break
if next_top == next_other:
yield next_top
next_top = next(sorted_top_posts, None)
next_other = next(other_posts, None)
continue
if next_top.date_utc > next_other.date_utc:
yield next_top
next_top = next(sorted_top_posts, None)
else:
yield next_other
next_other = next(other_posts, None)
class TopSearchResults:
"""

View File

@ -73,7 +73,7 @@ class TestInstaloaderAnonymously(unittest.TestCase):
self.L.download_hashtag(HASHTAG, NORMAL_MAX_COUNT)
def test_hashtag_paging(self):
for count, post in enumerate(instaloader.Hashtag.from_name(L.context, HASHTAG).get_posts()):
for count, post in enumerate(instaloader.Hashtag.from_name(self.L.context, HASHTAG).get_all_posts()):
print(post)
if count == PAGING_MAX_COUNT:
break