saret/DH
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

update folders

Browse Source
This commit is contained in:
Benny Saret
2023-04-12 12:34:56 +03:00
parent f592236971
commit df548fa29d
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
scrapping.py
View File

@@ -34,7 +34,8 @@ def _load_json_from_path(json_path: str) -> Dict:
def get_raw_english_texts_of_project(project_dirname: str, oracc_site: str = 'oracc.museum.upenn.edu') -> List[Dict]: def get_raw_english_texts_of_project(project_dirname: str, oracc_site: str = 'oracc.museum.upenn.edu') -> List[Dict]:
raw_jsons = list() raw_jsons = list()
all_paths = glob.glob(f'jsons_unzipped/{project_dirname}/**/corpusjson/*.json', recursive=True) all_paths = glob.glob(f'jsons_unzipped/{project_dirname}/**/corpusjson/*.json', recursive=True) + glob.glob(
f'jsons_unzipped/{project_dirname}/corpusjson/*.json', recursive=True)
# path = Path(os.path.join(JSONS_DIR, project_dirname, 'catalogue.json')) # path = Path(os.path.join(JSONS_DIR, project_dirname, 'catalogue.json'))
# if not os.path.isfile(path): # if not os.path.isfile(path):
# return raw_jsons # return raw_jsons