手把手教学：提取PDF各种表格文本数据（附代码）

pip install pdfplumber

import pdfplumber

pdf = pdfplumber.open("../pdfs/ca-warn-report.pdf")
p0 = pdf.pages[0]
im = p0.to_image()
im

table = p0.extract_table()
table[:3]

import pandas as pd
df = pd.DataFrame(table[1:], columns=table[0])
for column in ["Effective", "Received"]:
    df[column] = df[column].str.replace(" ", "")

import pdfplumber
report = pdfplumber.open("../pdfs/ag-energy-round-up-2017-02-24.pdf").pages[0]
im = report.to_image()
im

len(report.curves)
12
report.curves[0]

im.draw_lines(report.curves, stroke="red", stroke_width=2)

im.reset()
colors = [ "gray", "red", "blue", "green" ]
for i, curve in enumerate(report.curves):
    stroke = colors[i%len(colors)]
    im.draw_circles(curve["points"], radius=3, stroke=stroke, fill="white")
    im.draw_line(curve["points"], stroke=stroke, stroke_width=2)
im

import pdfplumber

pdf = pdfplumber.open("../pdfs/background-checks.pd")
p0 = pdf.pages[0]
im = p0.to_image()
im

im.reset().debug_tablefinder()

table_settings = {
    "vertical_strategy": "lines",
    "horizontal_strategy": "text",
    "intersection_x_tolerance": 15
}

im.reset().debug_tablefinder(table_settings)

table = p0.extract_table(table_settings)

for row in table[:5]:
    print(row)

core_table = table[3:3+56]
" • ".join(core_table[0])

" • ".join(core_table[-1])

COLUMNS = [
    "state",
    "permit",
    "handgun",
    "long_gun",
    "other",
    "multiple",
    "admin",
    "prepawn_handgun",
    "prepawn_long_gun",
    "prepawn_other",
    "redemption_handgun",
    "redemption_long_gun",
    "redemption_other",
    "returned_handgun",
    "returned_long_gun",
    "returned_other",
    "rentals_handgun",
    "rentals_long_gun",
    "private_sale_handgun",
    "private_sale_long_gun",
    "private_sale_other",
    "return_to_seller_handgun",
    "return_to_seller_long_gun",
    "return_to_seller_other",
    "totals"
]

def parse_value(i, x):
    if i == 0: return x
    if x == "": return None
    return int(x.replace(",", ""))

from collections import OrderedDict
def parse_row(row):
    return OrderedDict((COLUMNS[i], parse_value(i, cell))
        for i, cell in enumerate(row))

data = [ parse_row(row) for row in core_table ]
Now here's the first row, parsed:

data[0]

import pdfplumber
import re
from collections import OrderedDict

pdf = pdfplumber.open("../pdfs/san-jose-pd-firearm-sample.pdf")
p0 = pdf.pages[0]
im = p0.to_image()
im

im.reset().draw_rects(p0.chars)

text = p0.extract_text()
print(text)

core_pat = re.compile(r"LOCATION[\-\s]+(.*)\n\s+Flags = e", re.DOTALL)
core = re.search(core_pat, text).group(1)
print(core)

lines = core.split("\n")
line_groups = list(zip(lines[::2], lines[1::2]))
print(line_groups[0])

def parse_row(first_line, second_line):
    return OrderedDict([
        ("type", first_line[:20].strip()),
        ("item", first_line[21:41].strip()),
        ("make", first_line[44:89].strip()),
        ("model", first_line[90:105].strip()),
        ("calibre", first_line[106:111].strip()),
        ("status", first_line[112:120].strip()),
        ("flags", first_line[124:129].strip()),
        ("serial_number", second_line[0:13].strip()),
        ("report_tag_number", second_line[21:41].strip()),
        ("case_file_number", second_line[44:64].strip()),
        ("storage_location", second_line[68:91].strip())
    ])

parsed = [ parse_row(first_line, second_line)
    for first_line, second_line in line_groups ]

parsed[:2]

mport pandas as pd
columns = list(parsed[0].keys())
pd.DataFrame(parsed)[columns]