diff options
| author | yipstanley <stanley_yip@brown.edu> | 2019-07-29 14:05:40 -0400 |
|---|---|---|
| committer | yipstanley <stanley_yip@brown.edu> | 2019-07-29 14:05:40 -0400 |
| commit | a09d610e2a5c09e473b15be23c32f0c3cc370a17 (patch) | |
| tree | ed2452d68a2117c84e922f692ce0535077ce844b /src/scraping/buxton/scraper.py | |
| parent | 1c5c84c91742ff7822194519f536338bf96e6453 (diff) | |
| parent | 52da1fd396880603209b56cd49a590255d8b0b1f (diff) | |
fixes
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...") |