qurator-spk/page2tsv
1
0
Fork 0
mirror of https://github.com/qurator-spk/page2tsv.git synced 2025-07-03 23:29:52 +02:00
Code Issues Releases Wiki Activity

xlrd does not support xsls files anymore

Browse source
This commit is contained in:
Kai 2021-05-07 07:54:55 +02:00
parent 2bd4ae8d5a
commit ae93668bac
1 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tsvtools/cli.py
View file

@ -267,7 +267,11 @@ def find_entities(tsv_file, tsv_out_file, ner_rest_endpoint, ned_rest_endpoint,
"\n\ndefault: NERD.") "\n\ndefault: NERD.")
def make_page2tsv_commands(xls_file, directory, purpose): def make_page2tsv_commands(xls_file, directory, purpose):
if xls_file is not None: if xls_file is not None:
df = pd.read_excel(xls_file)
if xls_file.endswith(".xls"):
df = pd.read_excel(xls_file)
else:
df = pd.read_excel(xls_file, engine='openpyxl')
for _, row in df.iterrows(): for _, row in df.iterrows():
print('page2tsv $(OPTIONS) {}.xml {}.tsv --image-url={} --scale-factor={} --purpose={}'. print('page2tsv $(OPTIONS) {}.xml {}.tsv --image-url={} --scale-factor={} --purpose={}'.