多页PDF表格提取不全求助：仅获取2页及页眉数据

尝试提取多页PDF中的表格，但目前仅能获取2页数据及页眉信息。已将源PDF、输出CSV文件、代码文本文件整理，输出结果已存入CSV文件，目标是读取PDF中的全部数据。

当前使用的代码 #

import tabula
import requests
import csv
import pandas as pd

import re
import parse
import pdfplumber
from collections import namedtuple
import datetime
from datetime import date
import os
import glob
import shutil
from os import path

# 使用pdfplumber提取港口名称、品级名称和报告月份，用于后续数据拼接

# ------------------------------------文件名
file = "C:\\Users\\xxx\\Downloads\\test.pdf"

lines = []

pnames = []
gnames = []
mreports = []
with pdfplumber.open(file) as pdf:
    for page in pdf.pages:
        try:
            text = page.extract_text()
        except:
            text = ''
        if text is not None:
            liness = text.split('\n')
            lines += liness

for li in lines:
    if "Port:" in li:
        li = li.replace("Port:", "").strip()
        li_new = li.split("Month Reporting:")[-0].strip()
        m_repor = li.split("Month Reporting:")[-1].strip()

        if "Grade Name:" in li_new:
            g_name = li_new.split("Grade Name:")[-1].strip()
            p_name = li_new.split("Grade Name:")[0].strip()
            print(li_new)
        else:
            g_name = li_new.split()[1:]
            g_name = ' '.join(g_name).strip()
            p_name = li_new.split()[0].strip()
        pnames.append(p_name)
        gnames.append(g_name)
        mreports.append(m_repor)
print("PortName: ", len(pnames))
print("GradeName: ", len(gnames))
print("MonthReporting: ", len(mreports))

# 使用tabula提取PDF中所有表格并清洗，用于最终拼接
df = tabula.read_pdf(file, pages='all')
final_list = [
["PORT NAME", "GRADE NAME", "MONTH REPORTING", "BL DATE", "VESSEL", "DESTINATION", "CHARTERERS", "API"]]
# final_list=[]
print(final_list)
last_df = len(df)
print("Length of tables: ", last_df)

for i in range(0, len(pnames)):
    op_df = df[i]
    op_df = op_df.dropna(how='all')
    op_df_list = op_df.values.tolist()

    for li in op_df_list:
        if str(li[0]) == "nan":
            li = li[1:]
        else:
            print("check this case")
            print(li)
        li.insert(0, pnames[i])
        li.insert(1, gnames[i])
        li.insert(2, mreports[i])
        print(li)
        if "BL Date" in li:
            pass
        else:
            final_list.append(li)
df_2 = pd.DataFrame(final_list)
df_2.columns = df_2.iloc[0]
df_2 = df_2[1:]
max_row=len(df_2)
curr_date = datetime.datetime.now()
created_date = curr_date.strftime('%d-%b-%y')
for row in range(max_row):
    df_2['created_by'] = 'created by'
    df_2['created_date'] = created_date

print(df_2)
df_2.rename(
columns={'PORT NAME': 'port_name', 'GRADE NAME': 'crude', 'MONTH REPORTING': 'reporting_month', 'BL DATE': 'bl_date',
'VESSEL': 'vessel', 'DESTINATION': 'destination',
'CHARTERERS': 'charterer', 'API': 'api'}, inplace=True)

df_2 = df_2.reindex(
columns=["port_name", "crude", "reporting_month", "bl_date", "vessel", "destination", "Charterer",
"api"])

# return df_2


df_2.to_csv('Outputfile.csv', index=False)
print("Sucessfully generated output CSV")

尝试过的其他代码（无法适配现有逻辑） #

import pdfplumber
import pandas as pd
 

pdf_file = "test.pdf"
with pdfplumber.open(pdf_file) as pdf:
    lst = [p.extract_table() for p in pdf.pages]
 
flat_list = [item for sublist in lst[:3] for item in sublist]
df = pd.DataFrame(flat_list)
df.columns = df.iloc[0]
df = df[1:]

内容的提问来源于stack exchange，提问作者Shree S