read_pdf_plt/testplumber.py

import pdfplumber
import pandas as pd
import numpy as np;
basePath = "D:/mydocument/myproject/git/busscredit/Crerdai/";
pdf_path = basePath+"闻海雁532329198801060347.pdf"
# pdf_path = basePath+"雷雨晴130630199006130027.pdf"
# pdf_path=basePath+"杨安140402197102111236.pdf"
# pdf_path=basePath+"刘盼兰130133198912261210.pdf"
# pdf_path=basePath+"马维强130521198604045272.pdf"
pdf_path=basePath+"郑晨晨130681199008205811.pdf"
# pdf_path = basePath + "人行征信模拟数据报告.pdf"

reportTime=None;
reportTimeCn="报告时间："
queryreq = {}
identity = {}

queryreqDf=pd.DataFrame;#被查询信息
identityDf=pd.DataFrame;#
addressDf=pd.DataFrame;
mateDf=pd.DataFrame;
CREDITSUMMARYCUE_df = pd.DataFrame;
FIRSTLOANOPENMONTH_df=pd.DataFrame;
FIRSTLOANCARDOPENMONTH_df=pd.DataFrame;

FIRSTLOANOPENMONTH = "";#首笔贷款账龄
FIRSTLOANCARDOPENMONTH=""#首笔贷记卡账龄

OVERDUESUM_df=pd.DataFrame;#逾期透支信息汇总
SHAREANDDEBT_loan_df=pd.DataFrame;#非循环贷账户信息汇总
SHAREANDDEBT_creditCard_df=pd.DataFrame;#非循环贷账户信息汇总
RECORDSUMMARY_df = pd.DataFrame;#查询记录汇总_个人征信
RECORDDETAIL_df = pd.DataFrame;#查询记录明细

def parseQueryreq(reportTime):
    queryreq["reportTime"]=reportTime.split("：")[1];

headers_queryreq = ["被查询者姓名","被查询者证件类型","被查询者证件号码","查询机构","查询原因"];
header_identity=['性别', None, '出生日期', '婚姻状况', '学历', '学位', '就业状况', '国籍', '电子邮箱']
header_address=['通讯地址', None, None, None, None, '户籍地址', None, None, None]
header_mate = ['姓名', '证件类型', '证件号码', '工作单位', '联系电话']
header_CREDITSUMMARYCUE=['业务类型', None, '账户数', '首笔业务发放月份']
header_OVERDUESUM=['账户类型', '账户数', '月份数', '单月最高逾期/透支总额', '最长逾期/透支月数']
header_SHAREANDDEBT_loan=['管理机构数', '账户数', '授信总额', '余额', '最近6个月平均应还款']
header_SHAREANDDEBT_creditCard=['发卡机构数', '账户数', '授信总额', '单家机构最高\n授信额', '单家机构最低\n授信额', '已用额度', '最近6个月平\n均使用额度']
header_RECORDSUMMARY=['贷款审批', '信用卡审批', '贷款审批', '信用卡\n审批', '本人查询', '贷后管理', '担保资格\n审查', '特约商户\n实名审查']
header_RECORDDETAIL=['查询日期', '查询机构', '查询原因'] #查询记录明细
headers = [0] * 100
ignoreText=["异议信息提示","信息主体"]

def isIgnore(text):
    for txt in ignoreText:
        if text.find(txt)>=0:
            return True;
    return False;

#根据列确定表头
#判断条件需要修改
def hasHeader(headers,rows):
    text = rows[0]
    for header in headers:
        if header == text:
            return True
    return False;

def hasHeaderIndex(headers,rows,index):
    text = rows[index]
    for header in headers:
        if header == text:
            return True
    return False;

def headerOf(headers,entityHeader):
    for header in headers:
        if str(entityHeader).find(header)>=0:
            return True
    return False;
def getMinMonth(FIRSTLOANOPENMONTH_df):
    FIRSTLOANOPENMONTH_values = [];
    FIRSTLOANOPENMONTH = ""
    for value in FIRSTLOANOPENMONTH_df.values:
        if value == '--':
            continue
        FIRSTLOANOPENMONTH_values.append(value)
    if len(FIRSTLOANOPENMONTH_values)>0:
        far = np.array(FIRSTLOANOPENMONTH_values);
        findex = np.argmax(far)
        FIRSTLOANOPENMONTH = FIRSTLOANOPENMONTH_values[findex][0];
    return FIRSTLOANOPENMONTH;
with pdfplumber.open(pdf_path) as pdf:
    for page in pdf.pages:
        # first_page = pdf.pages[1]
        for table in page.extract_tables():
            df = pd.DataFrame(table)
            # 第一列当成表头：
            # df = pd.DataFrame(table[1:],columns=table[0])
            # print(df)
            for rows in table:
                print(rows)
                #         if col.find(reportTimeCn)>=0:
                #             reportTime = col;
                #             parseQueryreq(reportTime)
                            # print(queryreq)
                # if hasHeader(headers_queryreq,rows):
                #     queryreqDf = df;
                #     # print(queryreqDf)
                #     break;
                # elif hasHeader(header_identity,rows):
                #     identityDf = df[:2];
                #     # print(identityDf)
                #     # addressDf = pd.DataFrame(table,columns=header_address)[['通讯地址','户籍地址']]
                #     addressDf = df.iloc[2:4,[0,5]]
                #     break;
                # elif hasHeader(header_mate,rows):
                #     mateDf = df;
                #     break;
                # elif hasHeader(header_CREDITSUMMARYCUE,rows):
                #     CREDITSUMMARYCUE_df = df;
                #     #首笔贷款发放月份,所有行第三列
                #     #CREDITSUMMARYCUE_df[~CREDITSUMMARYCUE_df[1:4].iloc[:,[3]].isin(['--'])]
                #     FIRSTLOANOPENMONTH_df=CREDITSUMMARYCUE_df[1:4].iloc[:,[3]]
                #     FIRSTLOANOPENMONTH = getMinMonth(FIRSTLOANOPENMONTH_df)
                #     FIRSTLOANCARDOPENMONTH_df = CREDITSUMMARYCUE_df[4:6].iloc[:,[3]]
                #     FIRSTLOANCARDOPENMONTH = getMinMonth(FIRSTLOANCARDOPENMONTH_df)
                #     print("贷款账龄（月数）："+FIRSTLOANOPENMONTH);
                #     print("信用卡账龄（月数）：" + FIRSTLOANCARDOPENMONTH);
                #     #.min
                #     break;
                # elif hasHeader(header_CREDITSUMMARYCUE,rows):#信贷交易信息提示
                #     CREDITSUMMARYCUE_df = df;
                # elif hasHeader(header_SHAREANDDEBT_loan,rows):# 非循环贷账户信息汇总
                #     SHAREANDDEBT_loan_df = df;
                # elif hasHeader(header_SHAREANDDEBT_creditCard,rows):# 非循环贷账户信息汇总
                #     SHAREANDDEBT_creditCard_df = df;
                # elif hasHeader(header_RECORDSUMMARY,rows):# 非循环贷账户信息汇总
                #     RECORDSUMMARY_df = df;
                # elif len(rows)>1 and hasHeaderIndex(header_RECORDDETAIL,rows,1):# 查询记录明细
                #     RECORDDETAIL_df = df;
                #     print(RECORDDETAIL_df)