19 lines
711 B
Python
19 lines
711 B
Python
import sys, json
|
|
sys.path.insert(0, ".")
|
|
from pathlib import Path
|
|
import smart_extractor as se
|
|
from _lines import separator_barriers
|
|
|
|
D = Path("output/AndhraJyothi_Siddipet District_20260602_20260603_144919/pages")
|
|
png = D / "page_001.png"
|
|
regs0 = json.loads((D / "page_001.regions.json").read_text())["regions"]
|
|
regs = se.drop_masthead_regions(regs0, "andhra_jyothi", 1, png)
|
|
ds = se.find_article_starts_by_dateline(regs, str(png), "andhra_jyothi")
|
|
bars = separator_barriers(str(png), regs)
|
|
bl = se.cluster_all_article_blocks(regs, dateline_starts=ds, sep_lines=bars)
|
|
owner = {}
|
|
for b in bl:
|
|
for m in b["members"]:
|
|
owner[m] = b["anchor_id"]
|
|
print("R76 ->", owner.get(76), " R68 ->", owner.get(68))
|