bellingcat/auto-archiver
1
0
Fork 0
mirror of https://github.com/bellingcat/auto-archiver.git synced 2026-06-13 05:38:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

improving insta archiver

Browse Source
This commit is contained in:
msramalho
2024-02-23 15:37:28 +00:00
parent 5b9bc4919a
commit 70075a1e5e
2 changed files with 13 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/auto_archiver/archivers/instagram_api_archiver.py
View File

@@ -102,10 +102,18 @@ class InstagramAPIArchiver(Archiver):
logger.error(f"Error downloading stories for {username}: {e}")
# download all posts
self.download_all_posts(result, user_id)
try:
self.download_all_posts(result, user_id)
except Exception as e:
result.append("errors", f"Error downloading posts for {username}")
logger.error(f"Error downloading posts for {username}: {e}")
# download all tagged
self.download_all_tagged(result, user_id)
try:
self.download_all_tagged(result, user_id)
except Exception as e:
result.append("errors", f"Error downloading tagged posts for {username}")
logger.error(f"Error downloading tagged posts for {username}: {e}")
# download all highlights
try:
@@ -243,8 +251,8 @@ class InstagramAPIArchiver(Archiver):
if self.minimize_json_output:
del item["clips_metadata"]
if code := item.get("code"):
result.set("url", f"https://www.instagram.com/p/{code}/")
if code := item.get("code") and not result.get("url"):
result.set_url(f"https://www.instagram.com/p/{code}/")
resources = item.get("resources", item.get("carousel_media", []))
item, media, media_id = self.scrape_media(item, context)