【使用python获取pdf所需数据】_python爬取pdf指定内容

一：本文思路

1 代码

2 内容

采用代码、数据、结果结合的方式按操作顺序给出

二：正文

1 安装pdfplumber库

2 将pdf文件放入指定文件夹

此文件夹只用于存储pdf文件

3 代码部分

tips：运行前需要修改文件存放与读取地址。此代码会生成pdf读取的初始数据进行存储，再读取初始数据进行数据处理。

import pandas as pd
import warnings
import pdfplumber
import os
warnings.filterwarnings("ignore")


#自动导出文件夹对应的PDF数据
dir_path = r'C:\Users\24655\Desktop\python知识管理\python脚本和算法\脚本\read_pdf\数据'
path = []
for i,j,k in os.walk(dir_path):
    for m in range(len(k)):
        path.append(str(i)+'\\'+str(k[m]))
    for l in range(len(k)):
        with pdfplumber.open(path[l]) as pdf:
            #输出pdf隐藏信息
            #print(pdf.metadata)
            # 第一页pdfplumber.Page实例
            first_page = pdf.pages[0]
            # second_page = pdf.pages[1]
            text = first_page.extract_text()
            with open(r'C:\Users\24655\Desktop\python知识管理\python脚本和算法\脚本\read_pdf\数据\{}.csv'.format(k[l]),'w') as file:
                        file.write(str(text)+'/n')
    df_final = pd.DataFrame()
    for im in range(len(k)):
        #PDF导出的数据清洗
        df = pd.read_csv(r'C:\Users\24655\Desktop\python知识管理\python脚本和算法\脚本\read_pdf\数据\{}.csv'.format(k[im]),encoding = 'gbk')
        # print(df)
        df = df.loc[2:11]
        # print(df)
        len_df_loc = df.loc[3].str.split(' ')[0] #解决pdf读取数据时，4s在与不在同一行导致的删除列错误
        # print(len(len_df_loc))
        if len(len_df_loc) <= 2:
            df.loc[3] = df.loc[3]+' '+df.loc[4]
            df.drop(index = [4,5,6,9],inplace = True)
        else:
            df.loc[3] = df.loc[3]+' '+df.loc[4]
            df.drop(index = [4,5,8],inplace = True)
        # print(df)
        df = df.admin.reset_index()
        df = df['admin'].str.split(' ',expand = True) #以表格形式切割数据
        # print(df)
        #清洗完的数据精准获取
        data_cell = []
        data_cell.append(k[im]) #地图名称
        split_df_1 = df.loc[3] #解决pdf读取数据时，4s在与不在同一行导致的删除列错误
        if len(split_df_1) <= 14:
            data_case_type = df.loc[3,2]
            data_cell.append(data_case_type) #项目类型
        else:
            data_case_type = df.loc[3,3]
            data_cell.append(data_case_type) #项目类型
        data_efficiency_of_the_car = df.loc[1,0]
        data_cell.append(data_efficiency_of_the_car) #车效
        data_efficiency_of_the_warehouse = df.loc[1,1]
        data_cell.append(data_efficiency_of_the_warehouse) #整仓效率
        data_Processing_time_for_a_single_container = df.loc[1,2]
        data_cell.append(data_Processing_time_for_a_single_container) #单箱处理时间
        data_the_number_of_car = df.loc[5,0]
        data_cell.append(data_the_number_of_car) #车数
        data_the_number_of_mc = df.loc[3,11]
        data_cell.append(data_the_number_of_mc) #任务数
        data_Workstation_type_of_inbound = df.loc[5,6]
        data_cell.append(data_Workstation_type_of_inbound) #出库工作站类型
        data_Workstation_number_of_inbound = df.loc[5,5]
        data_cell.append(data_Workstation_number_of_inbound) #出库工作站数量
        data_Conveyor_line = df.loc[5,9]
        data_cell.append(data_Conveyor_line) #是否有输送线
        # 解决pdf识别问题导致报告编码与任务名称粘在一起的问题
        split_df_1 = df.loc[3] #解决pdf读取数据时，4s在与不在同一行导致的删除列错误
        if len(split_df_1) <= 14:
            data_Pick_up_time_of_outbound = df.loc[3,8]
            data_cell.append(data_Pick_up_time_of_outbound) #出库拣货时间(h)
            data_total_time_of_Perform_a_task = df.loc[3,12]
            data_cell.append(data_total_time_of_Perform_a_task) #执行任务总时长(h)
            data_Times_the_speed = df.loc[3,3]
            data_cell.append(data_Times_the_speed) #倍速
        else:
            data_Pick_up_time_of_outbound = df.loc[3,9]
            data_cell.append(data_Pick_up_time_of_outbound) #出库拣货时间(h)
            data_total_time_of_Perform_a_task = df.loc[3,13]
            data_cell.append(data_total_time_of_Perform_a_task) #执行任务总时长(h)
            data_Times_the_speed = df.loc[3,4]
            data_cell.append(data_Times_the_speed) #倍速
        data_cell = pd.Series(data_cell)
        data_cell = pd.DataFrame(data_cell.T)
        data_cell = data_cell.T
        data_cell.columns = ['地图', '项目类型', '车效(箱//车)', '整仓效率(箱/)', '单箱处理耗时', '车数', '任务数', '出库工作站类型',
           '出库工作站数量', '是否有输送线', '出库拣货时间(h)', '执行任务总时长(h)', '倍速']
        df_final = pd.concat([df_final,data_cell])
    df_final = df_final.sort_values(by = '倍速',axis = 0,ascending = True)
    df_final.to_csv(r'C:\Users\24655\Desktop\python知识管理\python脚本和算法\脚本\read_pdf\数据\{}个pdf文件数据汇总.csv'.format(len(k)),index = False,encoding='gbk')
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92