diff options
| author | ab <abdullah_ahmed@brown.edu> | 2019-07-30 11:44:19 -0400 |
|---|---|---|
| committer | ab <abdullah_ahmed@brown.edu> | 2019-07-30 11:44:19 -0400 |
| commit | d58d66f29eae28ac8244f8c2bcaa423e0aa99743 (patch) | |
| tree | 6a34daa4fd4111470763f6b5c215c95fcd254f52 /src/scraping/buxton/scraper.py | |
| parent | 38b5d646e62535504eb8667b840bf36cd7f2f6d8 (diff) | |
| parent | ca91fe9e379fe3e2d48a0eb055415f008245ed31 (diff) | |
merged
Diffstat (limited to 'src/scraping/buxton/scraper.py')
| -rw-r--r-- | src/scraping/buxton/scraper.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/scraping/buxton/scraper.py b/src/scraping/buxton/scraper.py index 182b22a1a..1ff0e3b31 100644 --- a/src/scraping/buxton/scraper.py +++ b/src/scraping/buxton/scraper.py @@ -139,7 +139,7 @@ def write_text_doc(content): data_doc = { "_id": data_doc_guid, "fields": { - "proto": protofy("commonImportProto"), + "proto": protofy("textProto"), "data": { "Data": '{"doc":{"type":"doc","content":[{"type":"paragraph","content":[{"type":"text","text":"' + content + '"}]}]},"selection":{"type":"text","anchor":1,"head":1}' + '}', "__type": "RichTextField" @@ -235,7 +235,7 @@ def parse_document(file_name: str): count += 1 view_guids.append(write_image(pure_name, image)) copyfile(dir_path + "/" + image, dir_path + - "/" + image.replace(".", "_o.", 1)) + "/" + image.replace(".", "_o.", 1)) os.rename(dir_path + "/" + image, dir_path + "/" + image.replace(".", "_m.", 1)) print(f"extracted {count} images...") |