diff options
| author | Terry Truong <terry06890@gmail.com> | 2022-06-19 14:50:38 +1000 |
|---|---|---|
| committer | Terry Truong <terry06890@gmail.com> | 2022-06-19 14:50:38 +1000 |
| commit | 19c5a2b6c57b8c4245bb07773caa8df598b3feec (patch) | |
| tree | e944f66fff51448e75677982c3b3118856aeeb18 /backend/data/enwiki/downloadImgLicenseInfo.py | |
| parent | 8c8ed28c87e649f163aaa54899f4b00c9fc31224 (diff) | |
Make manual enwiki-desc-associations more flexible
Also enable getEnwikiImgData.py to skip already-processed wiki-ids
Diffstat (limited to 'backend/data/enwiki/downloadImgLicenseInfo.py')
| -rwxr-xr-x | backend/data/enwiki/downloadImgLicenseInfo.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/backend/data/enwiki/downloadImgLicenseInfo.py b/backend/data/enwiki/downloadImgLicenseInfo.py index 5d99573..8231fbb 100755 --- a/backend/data/enwiki/downloadImgLicenseInfo.py +++ b/backend/data/enwiki/downloadImgLicenseInfo.py @@ -33,7 +33,7 @@ if dbCur.execute("SELECT name FROM sqlite_master WHERE type='table' AND name='im # Get image names print("Reading image names") imgNames = set() -for (imgName,) in dbCur.execute("SELECT DISTINCT img_name FROM page_imgs"): +for (imgName,) in dbCur.execute("SELECT DISTINCT img_name FROM page_imgs WHERE img_name NOT NULL"): imgNames.add(imgName) print(f"Found {len(imgNames)} images") oldSz = len(imgNames) |
