问如何使用Python从PDF中提取表作为文本？

EN

import cv2

def find_tables(image):
    BLUR_KERNEL_SIZE = (17, 17)
    STD_DEV_X_DIRECTION = 0
    STD_DEV_Y_DIRECTION = 0
    blurred = cv2.GaussianBlur(image, BLUR_KERNEL_SIZE, STD_DEV_X_DIRECTION, STD_DEV_Y_DIRECTION)
    MAX_COLOR_VAL = 255
    BLOCK_SIZE = 15
    SUBTRACT_FROM_MEAN = -2

    img_bin = cv2.adaptiveThreshold(
        ~blurred,
        MAX_COLOR_VAL,
        cv2.ADAPTIVE_THRESH_MEAN_C,
        cv2.THRESH_BINARY,
        BLOCK_SIZE,
        SUBTRACT_FROM_MEAN,
    )
    vertical = horizontal = img_bin.copy()
    SCALE = 5
    image_width, image_height = horizontal.shape
    horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (int(image_width / SCALE), 1))
    horizontally_opened = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, horizontal_kernel)
    vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, int(image_height / SCALE)))
    vertically_opened = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, vertical_kernel)

    horizontally_dilated = cv2.dilate(horizontally_opened, cv2.getStructuringElement(cv2.MORPH_RECT, (40, 1)))
    vertically_dilated = cv2.dilate(vertically_opened, cv2.getStructuringElement(cv2.MORPH_RECT, (1, 60)))

    mask = horizontally_dilated + vertically_dilated
    contours, hierarchy = cv2.findContours(
        mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE,
    )

    MIN_TABLE_AREA = 1e5
    contours = [c for c in contours if cv2.contourArea(c) > MIN_TABLE_AREA]
    perimeter_lengths = [cv2.arcLength(c, True) for c in contours]
    epsilons = [0.1 * p for p in perimeter_lengths]
    approx_polys = [cv2.approxPolyDP(c, e, True) for c, e in zip(contours, epsilons)]
    bounding_rects = [cv2.boundingRect(a) for a in approx_polys]

    # The link where a lot of this code was borrowed from recommends an
    # additional step to check the number of "joints" inside this bounding rectangle.
    # A table should have a lot of intersections. We might have a rectangular image
    # here though which would only have 4 intersections, 1 at each corner.
    # Leaving that step as a future TODO if it is ever necessary.
    images = [image[y:y+h, x:x+w] for x, y, w, h in bounding_rects]
    return images

def cell_in_same_row(c1, c2):
    c1_center = c1[1] + c1[3] - c1[3] / 2
    c2_bottom = c2[1] + c2[3]
    c2_top = c2[1]
    return c2_top < c1_center < c2_bottom

orig_cells = [c for c in cells]
rows = []
while cells:
    first = cells[0]
    rest = cells[1:]
    cells_in_same_row = sorted(
        [
            c for c in rest
            if cell_in_same_row(c, first)
        ],
        key=lambda c: c[0]
    )

    row_cells = sorted([first] + cells_in_same_row, key=lambda c: c[0])
    rows.append(row_cells)
    cells = [
        c for c in rest
        if not cell_in_same_row(c, first)
    ]

# Sort rows by average height of their center.
def avg_height_of_center(row):
    centers = [y + h - h / 2 for x, y, w, h in row]
    return sum(centers) / len(centers)

rows.sort(key=avg_height_of_center)

import pandas as pd
import tabula
file = "filename.pdf"
path = 'enter your directory path here'  + file
df = tabula.read_pdf(path, pages = '1', multiple_tables = True)
print(df)

import camelot
tables = camelot.read_pdf('foo.pdf')

tables.export('foo.csv', f='csv', compress=False)

import camelot
import cProfile
import pstats
import tabula

cmd_tabula = "tabula.read_pdf('table.pdf', pages='1', lattice=True)"
prof_tabula = cProfile.Profile().run(cmd_tabula)
time_tabula = pstats.Stats(prof_tabula).total_tt

cmd_camelot = "camelot.read_pdf('table.pdf', pages='1', flavor='lattice')"
prof_camelot = cProfile.Profile().run(cmd_camelot)
time_camelot = pstats.Stats(prof_camelot).total_tt

print(time_tabula, time_camelot, time_camelot/time_tabula)

1.8495559890000015 11.057014036000016 5.978199147125147