diff options
| author | fawn <fangrui_tong@brown.edu> | 2019-07-30 16:52:12 -0400 |
|---|---|---|
| committer | fawn <fangrui_tong@brown.edu> | 2019-07-30 16:52:12 -0400 |
| commit | f7c0948910182f5f6cb2c10c216994e2bc7b91b0 (patch) | |
| tree | 6d443543c7475f4104bf7b8a3be788bb3ce2a3ec /src/scraping/buxton/scraper.py | |
| parent | 78999b8b35267db9236bbb69e7e90e8691c59ba9 (diff) | |
| parent | 8ca17d379ce7d3cc751408553b6819223d31a3e0 (diff) | |
merged
Diffstat (limited to 'src/scraping/buxton/scraper.py')
| -rw-r--r-- | src/scraping/buxton/scraper.py | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/src/scraping/buxton/scraper.py b/src/scraping/buxton/scraper.py index 182b22a1a..f0f45d8f9 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" @@ -235,8 +235,8 @@ 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)) - os.rename(dir_path + "/" + image, dir_path + + "/" + image.replace(".", "_o.", 1)) + copyfile(dir_path + "/" + image, dir_path + "/" + image.replace(".", "_m.", 1)) print(f"extracted {count} images...") |