Python Manipulate PDF

# Python Manipulate PDF using PyPDF2

#### Installation

```bash
pip install PyPDF2
```

#### Usage

Get PDF number of pages
```python
from PyPDF2 import PdfFileReader
pdf = PdfFileReader(open(PDF_NAME, 'rb'))
pdfNumPages = pdf.getNumPages()
```

Read PDF page(s) content
```python
from PyPDF2 import PdfFileReader
pdf = PdfFileReader(open(PDF_NAME, 'rb'))
pdfPage = pdf.getPage(PAGE_NUM)
```

Add PDF page to Writer buffer
```python
from PyPDF2 import PdfFileReader, PdfFileWriter
writer = PdfFileWriter()
pdf = PdfFileReader(open(pdf_name, 'rb'))
for j in range(pdf.getNumPages()):
    writer.addPage(pdf.getPage(j))
```

Add blank page to Writer buffer
```python
from PyPDF2 import PdfFileWriter
writer = PdfFileWriter()
writer.addBlankPage()
```

Merge multiple PDFs into a single PDF
```python
from PyPDF2 import PdfFileMerger
merger = PdfFileMerger()
for pdf in PDF_NAME_LIST:
    merger.append(pdf)
merger.write('merge.pdf')
```

#### Working Example

##### Aim:
- To combine a batch of dataset evaluation results into a single PDF
- As printing layout shrinks every 4 pages into a single page, so to add blank pages to maintain every dataset has number of page divisible by 4
- To name the output PDF as "Evaluation_yyyy-mm-dd.pdf"

##### Code:
```python
from PyPDF2 import PdfFileReader,PdfFileWriter
import os, glob, datetime

#### Define Functions #####
def gen_evaluation_pdf(target_dir=".",target_pattern = "*dataset_evaluation.pdf"):
    now = datetime.datetime.now()
    current_date = now.strftime("%Y-%m-%d")
    output_filename = f"Evaluation_{current_date}.pdf"
    gse_results = [i for i in os.listdir(target_dir) if "." not in i]
    pdf_count = 0
    output = PdfFileWriter()
    
    for gse_result in gse_results:
        pdf_name_list = glob.glob("./"+gse_result+"/"+target_pattern)
        if len(pdf_name_list):
            for i in range(len(pdf_name_list)):
                pdf_count += 1
                pdf_name = pdf_name_list[i]
                pdf = PdfFileReader(open(pdf_name, 'rb'))
                for j in range(pdf.getNumPages()):
                    output.addPage(pdf.getPage(j))

for j in range((4-pdf.getNumPages()) % 4):
                    output.addBlankPage()
    
    print(f"There are {pdf_count} evaluation pdfs found.")  
    
    with open(output_filename, "wb") as f_out:
        output.write(f_out)
    print("Job done!")

def get_evaluation_pdf(target_dir=".",target_pattern = "*dataset_evaluation.pdf"):
    gse_results = [i for i in os.listdir(target_dir) if "." not in i]
    pdfs = []
    page_sum = 0
    for gse_result in gse_results:
        pdf_name_list = glob.glob("./"+gse_result+"/"+target_pattern)
        if len(pdf_name_list)>1:
            for pdf_name in pdf_name_list:
                pdf = PdfFileReader(open(pdf_name,'rb'))
                page_sum += pdf.getNumPages()     
                pdf_name_ele = pdf_name.split("/")
                pdfs.append((pdf_name_ele[1].split("_")[0],pdf_name_ele[2].replace("_dataset_evaluation.pdf","")))
    return pdfs,page_sum

##########################

gen_evaluation_pdf()

for i,j in get_evaluation_pdf()[0]:
    print(i,"\t",j.replace("_WB"," vs Control").replace("_PBMC"," vs Control"),sep="")
    
```

#### Source

**Documentation link**: [PyPDF2 Documentation](https://pythonhosted.org/PyPDF2/)

Back to Contents

Loading