File size: 2,177 Bytes
41c7a59 9cba22c 41c7a59 2d09c38 41c7a59 79ada0b 41c7a59 79ada0b 41c7a59 79ada0b 41c7a59 6be8543 79ada0b 41c7a59 79ada0b b5e86a6 41c7a59 79ada0b 41c7a59 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
from io import BytesIO
from pptx import Presentation
class RAGFlowPptParser(object):
def __init__(self):
super().__init__()
def __extract(self, shape):
if shape.shape_type == 19:
tb = shape.table
rows = []
for i in range(1, len(tb.rows)):
rows.append("; ".join([tb.cell(
0, j).text + ": " + tb.cell(i, j).text for j in range(len(tb.columns)) if tb.cell(i, j)]))
return "\n".join(rows)
if shape.has_text_frame:
return shape.text_frame.text
if shape.shape_type == 6:
texts = []
for p in sorted(shape.shapes, key=lambda x: (x.top // 10, x.left)):
t = self.__extract(p)
if t:
texts.append(t)
return "\n".join(texts)
def __call__(self, fnm, from_page, to_page, callback=None):
ppt = Presentation(fnm) if isinstance(
fnm, str) else Presentation(
BytesIO(fnm))
txts = []
self.total_page = len(ppt.slides)
for i, slide in enumerate(ppt.slides):
if i < from_page:
continue
if i >= to_page:
break
texts = []
for shape in sorted(
slide.shapes, key=lambda x: ((x.top if x.top is not None else 0) // 10, x.left)):
txt = self.__extract(shape)
if txt:
texts.append(txt)
txts.append("\n".join(texts))
return txts
|