qurator-spk/page2tsv
1
0
Fork 0
mirror of https://github.com/qurator-spk/page2tsv.git synced 2026-03-15 11:42:06 +01:00
Code Issues Releases Wiki Activity

add support for image url in page meta data

Browse source
This commit is contained in:
Kai Labusch 2026-02-24 10:49:52 +01:00
parent 5d9d9f03cf
commit b90d1fe56a
2 changed files with 9 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

8
qurator/tsvtools/cli.py
View file

@ -403,6 +403,14 @@ def page2tsv(page_xml_file, tsv_out_file, purpose, image_url, ner_rest_endpoint,
tsv = [] tsv = []
line_info = [] line_info = []
if image_url == 'http://empty':
creator = pcgts.Metadata.get_Creator()
neat_url_ma = re.match(r"(.*)\|NEAT_URL:(.*?)\|.*", creator)
if neat_url_ma:
image_url = neat_url_ma.group(2)
_unicode_normalize = unicode_normalize _unicode_normalize = unicode_normalize
if normalization_file is not None: if normalization_file is not None:

2
requirements.txt
View file

@ -1,3 +1,3 @@
ocrd >= 2.23.2 ocrd >= 2.23.2
pandas pandas
qurator-sbb-utils @ git+https://github.com/qurator-spk/sbb_utils.git qurator-sbb-utils @ git+https://github.com/qurator-spk/sbb_utils.git