diff --git a/site/parser.py b/site/parser.py
index be3ad49..e6a9053 100644
--- a/site/parser.py
+++ b/site/parser.py
@@ -123,30 +123,6 @@ def _parse_doc(file_bytes: bytes) -> dict:
def _parse_pdf(file_bytes: bytes) -> dict:
result = {"elements": [], "errors": []}
-
- # Попробовать camelot (pdfium, без системных зависимостей)
- tables_from_camelot = False
- try:
- import camelot
- for flavor in ("lattice", "stream"):
- try:
- ctables = camelot.read_pdf(io.BytesIO(file_bytes), pages="all", flavor=flavor)
- for ct in ctables:
- rows = [list(ct.df.columns)] + ct.df.values.tolist()
- result["elements"].append({
- "type": "table",
- "rows": rows,
- "page": ct.page,
- })
- tables_from_camelot = True
- except Exception:
- pass
- except ImportError:
- result["errors"].append("camelot not installed, using pdfplumber")
- except Exception as e:
- result["errors"].append(f"camelot error: {e}")
-
- # pdfplumber: текст + таблицы (если tabula не сработал)
try:
import pdfplumber
with pdfplumber.open(io.BytesIO(file_bytes)) as pdf:
@@ -163,18 +139,16 @@ def _parse_pdf(file_bytes: bytes) -> dict:
"text": line,
"page": pn,
})
- if not tables_from_camelot:
- tables = page.extract_tables()
- for tbl in tables:
- if tbl:
- result["elements"].append({
- "type": "table",
- "rows": tbl,
- "page": pn,
- })
+ tables = page.extract_tables()
+ for tbl in tables:
+ if tbl:
+ result["elements"].append({
+ "type": "table",
+ "rows": tbl,
+ "page": pn,
+ })
except Exception as e:
result["errors"].append(f"pdfplumber: {e}")
-
return result
diff --git a/site/templates/upload.html b/site/templates/upload.html
index 04f10e6..eeea7e9 100644
--- a/site/templates/upload.html
+++ b/site/templates/upload.html
@@ -59,7 +59,7 @@
 }})
-
Сверка договоров v1.35
+
Сверка договоров v1.36