使用python提取pdf表中包含的文本的最佳方法是什么? [英] What is the best way to extract text contained within a table in a pdf using python?
问题描述
我正在构建一个程序，以从pdf中提取文本，将其以结构化格式放置，然后发送给数据库.我大约有1400个单独的pdf文件，它们都遵循类似的格式，但是这些文件所总结的措辞和计划设计上的细微差别使它变得棘手.
我在python中使用了几个不同的pdf阅读器，包括tabula-py和pdfminer，但是它们都不完全符合我的意愿. Tabula很好地阅读了所有文本，但是它拉动了所有内容，因为它明确地水平放置，不包括某些文本包裹在框中的事实.例如，如果您打开样本SBC，则我将其附加为总自付额是多少?". Tabula将在整体$ 500/个人或...的总金额是多少"中读到，忽略了自付额"一词确实是第一句话的一部分的事实. (请注意，我正在使用的文件是pdf，但是我已经附加了jpeg，因为我不知道如何附加pdf.)
import tabula
df = tabula.read_pdf(*filepath*, pandas_options={'header': None))
print(df.iloc[0][0])
print(df)
最后，我真的很想能够解析每个框中的文本，以便我可以更好地识别哪些值属于可抵扣，自付费用，自付费用/共同保险等.我认为也许某种OCR可以让我识别出蓝色矩形中包含的PDF的哪些部分，然后从那里拉出字符串，但是我真的不知道从哪里开始.解决方案
我认为，执行所需操作的最佳方法是查找并隔离文件中的单元格，然后将OCR应用于每个单独的单元格.
为此，有很多解决方案，我从此答案中获取了代码，并花了一些时间并带有参数以获取下面的输出(尚不完善，但是您可以自己对其进行一些调整).
import os
import cv2
import imutils
# This only works if there's only one table on a page
# Important parameters:
# - morph_size
# - min_text_height_limit
# - max_text_height_limit
# - cell_threshold
# - min_columns
def pre_process_image(img, save_in_file, morph_size=(23, 23)):
# get rid of the color
pre = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Otsu threshold
pre = cv2.threshold(pre, 250, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
# dilate the text to make it solid spot
cpy = pre.copy()
struct = cv2.getStructuringElement(cv2.MORPH_RECT, morph_size)
cpy = cv2.dilate(~cpy, struct, anchor=(-1, -1), iterations=1)
pre = ~cpy
if save_in_file is not None:
cv2.imwrite(save_in_file, pre)
return pre
def find_text_boxes(pre, min_text_height_limit=20, max_text_height_limit=120):
# Looking for the text spots contours
contours, _ = cv2.findContours(pre, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
# Getting the texts bounding boxes based on the text size assumptions
boxes = []
for contour in contours:
box = cv2.boundingRect(contour)
h = box[3]
if min_text_height_limit < h < max_text_height_limit:
boxes.append(box)
return boxes
def find_table_in_boxes(boxes, cell_threshold=100, min_columns=3):
rows = {}
cols = {}
# Clustering the bounding boxes by their positions
for box in boxes:
(x, y, w, h) = box
col_key = x // cell_threshold
row_key = y // cell_threshold
cols[row_key] = [box] if col_key not in cols else cols[col_key] + [box]
rows[row_key] = [box] if row_key not in rows else rows[row_key] + [box]
# Filtering out the clusters having less than 2 cols
table_cells = list(filter(lambda r: len(r) >= min_columns, rows.values()))
# Sorting the row cells by x coord
table_cells = [list(sorted(tb)) for tb in table_cells]
# Sorting rows by the y coord
table_cells = list(sorted(table_cells, key=lambda r: r[0][1]))
return table_cells
def build_lines(table_cells):
if table_cells is None or len(table_cells) <= 0:
return [], []
max_last_col_width_row = max(table_cells, key=lambda b: b[-1][2])
max_x = max_last_col_width_row[-1][0] + max_last_col_width_row[-1][2]
max_last_row_height_box = max(table_cells[-1], key=lambda b: b[3])
max_y = max_last_row_height_box[1] + max_last_row_height_box[3]
hor_lines = []
ver_lines = []
for box in table_cells:
x = box[0][0]
y = box[0][1]
hor_lines.append((x, y, max_x, y))
for box in table_cells[0]:
x = box[0]
y = box[1]
ver_lines.append((x, y, x, max_y))
(x, y, w, h) = table_cells[0][-1]
ver_lines.append((max_x, y, max_x, max_y))
(x, y, w, h) = table_cells[0][0]
hor_lines.append((x, max_y, max_x, max_y))
return hor_lines, ver_lines
if __name__ == "__main__":
in_file = os.path.join(".", "test.jpg")
pre_file = os.path.join(".", "pre.png")
out_file = os.path.join(".", "out.png")
img = cv2.imread(os.path.join(in_file))
pre_processed = pre_process_image(img, pre_file)
text_boxes = find_text_boxes(pre_processed)
cells = find_table_in_boxes(text_boxes)
hor_lines, ver_lines = build_lines(cells)
# Visualize the result
vis = img.copy()
# for box in text_boxes:
# (x, y, w, h) = box
# cv2.rectangle(vis, (x, y), (x + w - 2, y + h - 2), (0, 255, 0), 1)
for line in hor_lines:
[x1, y1, x2, y2] = line
cv2.line(vis, (x1, y1), (x2, y2), (0, 0, 255), 1)
for line in ver_lines:
[x1, y1, x2, y2] = line
cv2.line(vis, (x1, y1), (x2, y2), (0, 0, 255), 1)
cv2.imwrite(out_file, vis)
I'm constructing a program to extract text from a pdf, put it in a structured format, and send it off to a database. I have roughly 1,400 individual pdfs that all follow a similar format, but nuances in the verbiage and plan designs that the documents summarize make it tricky.
I've played around with a couple different pdf readers in python including tabula-py and pdfminer but none of them are quite getting to what I'd like to do. Tabula reads in all of the text very well, however it pulls everything as it explicitly lays horizontally, excluding the fact that some of the text is wrapped in a box. For example, if you open up the sample SBC I have attached where it reads "What is the overall deductible?" Tabula will read in "What is the overall $500/Individual or..." skipping the fact that the word "deductible" is really part of the first sentence. (Note the files I'm working with are pdfs but I've attached a jpeg because I couldn't figure out how to attach a pdf.)
import tabula
df = tabula.read_pdf(*filepath*, pandas_options={'header': None))
print(df.iloc[0][0])
print(df)
In the end, I'd really like to be able to parse out the text within each box so that I can better identify what values belong to deductible, out-of-pocket limts, copays/coinsurance, etc. I thought possibly some sort of OCR would allow me to recognize which parts of the PDF are contained in the blue rectangles and then pull the string from there, but I really don't know where to start with that.Sample SBC
I think that the best way to do what you need is to find and isolate the cells in the file and then apply OCR to each individual cell.
There are a number of solutions in SO for that, I got the code from this answer and played around a little with the parameters to get the output below (not perfect yet, but you can tweak it a little bit yourself).
import os
import cv2
import imutils
# This only works if there's only one table on a page
# Important parameters:
# - morph_size
# - min_text_height_limit
# - max_text_height_limit
# - cell_threshold
# - min_columns
def pre_process_image(img, save_in_file, morph_size=(23, 23)):
# get rid of the color
pre = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Otsu threshold
pre = cv2.threshold(pre, 250, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
# dilate the text to make it solid spot
cpy = pre.copy()
struct = cv2.getStructuringElement(cv2.MORPH_RECT, morph_size)
cpy = cv2.dilate(~cpy, struct, anchor=(-1, -1), iterations=1)
pre = ~cpy
if save_in_file is not None:
cv2.imwrite(save_in_file, pre)
return pre
def find_text_boxes(pre, min_text_height_limit=20, max_text_height_limit=120):
# Looking for the text spots contours
contours, _ = cv2.findContours(pre, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
# Getting the texts bounding boxes based on the text size assumptions
boxes = []
for contour in contours:
box = cv2.boundingRect(contour)
h = box[3]
if min_text_height_limit < h < max_text_height_limit:
boxes.append(box)
return boxes
def find_table_in_boxes(boxes, cell_threshold=100, min_columns=3):
rows = {}
cols = {}
# Clustering the bounding boxes by their positions
for box in boxes:
(x, y, w, h) = box
col_key = x // cell_threshold
row_key = y // cell_threshold
cols[row_key] = [box] if col_key not in cols else cols[col_key] + [box]
rows[row_key] = [box] if row_key not in rows else rows[row_key] + [box]
# Filtering out the clusters having less than 2 cols
table_cells = list(filter(lambda r: len(r) >= min_columns, rows.values()))
# Sorting the row cells by x coord
table_cells = [list(sorted(tb)) for tb in table_cells]
# Sorting rows by the y coord
table_cells = list(sorted(table_cells, key=lambda r: r[0][1]))
return table_cells
def build_lines(table_cells):
if table_cells is None or len(table_cells) <= 0:
return [], []
max_last_col_width_row = max(table_cells, key=lambda b: b[-1][2])
max_x = max_last_col_width_row[-1][0] + max_last_col_width_row[-1][2]
max_last_row_height_box = max(table_cells[-1], key=lambda b: b[3])
max_y = max_last_row_height_box[1] + max_last_row_height_box[3]
hor_lines = []
ver_lines = []
for box in table_cells:
x = box[0][0]
y = box[0][1]
hor_lines.append((x, y, max_x, y))
for box in table_cells[0]:
x = box[0]
y = box[1]
ver_lines.append((x, y, x, max_y))
(x, y, w, h) = table_cells[0][-1]
ver_lines.append((max_x, y, max_x, max_y))
(x, y, w, h) = table_cells[0][0]
hor_lines.append((x, max_y, max_x, max_y))
return hor_lines, ver_lines
if __name__ == "__main__":
in_file = os.path.join(".", "test.jpg")
pre_file = os.path.join(".", "pre.png")
out_file = os.path.join(".", "out.png")
img = cv2.imread(os.path.join(in_file))
pre_processed = pre_process_image(img, pre_file)
text_boxes = find_text_boxes(pre_processed)
cells = find_table_in_boxes(text_boxes)
hor_lines, ver_lines = build_lines(cells)
# Visualize the result
vis = img.copy()
# for box in text_boxes:
# (x, y, w, h) = box
# cv2.rectangle(vis, (x, y), (x + w - 2, y + h - 2), (0, 255, 0), 1)
for line in hor_lines:
[x1, y1, x2, y2] = line
cv2.line(vis, (x1, y1), (x2, y2), (0, 0, 255), 1)
for line in ver_lines:
[x1, y1, x2, y2] = line
cv2.line(vis, (x1, y1), (x2, y2), (0, 0, 255), 1)
cv2.imwrite(out_file, vis)
这篇关于使用python提取pdf表中包含的文本的最佳方法是什么?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
