[Python] 批量抓取公众号文章导出pdf生成书签

先上代码

from PyPDF2 import  PdfFileReader, PdfFileWriter,PdfFileMerger
file_writer = PdfFileWriter()
merger = PdfFileMerger()
num = 0
for root, dirs, files in os.walk('.'):
    for name in files:
        if name.endswith(".pdf"):
            print(name)
            file_reader = PdfFileReader(f"{name}")
            file_writer.addBookmark(html.unescape(name).replace('.pdf',''), num, parent=None)
            for page in range(file_reader.getNumPages()):
                num += 1
                file_writer.addPage(file_reader.getPage(page))
with open(r"公众号文章合集.pdf",'wb') as f:
    file_writer.write(f)

效果如图，以莫言的公众号为例，点击左侧书签跳转到对应文章：

当然也可以将pdf的书签导出到excel，代码：

def bookmark_export(lines):
    bookmark = ''
    for line in lines:
        if isinstance(line, dict):
            bookmark += line['/Title'] + ','+str(line['/Page']+1)+'\n'
        else:
            bookmark_export(line)
    return bookmark
with open('公众号文章合集.pdf', 'rb') as f:
    lines = PdfFileReader(f).getOutlines()
    bookmark = bookmark_export(lines)
with open('公众号文章合集.csv', 'a+', encoding='utf-8-sig') as f:
    f.write(bookmark)