python 从Url获取pdf内容：

def getpdfContent(url):
    import urllib3
    import io
    import PyPDF2
    urllib3.disable_warnings()
    contents = ''
    # url = 'https://www.apc-paris.com/system/files/file_fields/2022/04/14/apc-trophees-coachcopro-vf.pdf'
    with urllib3.PoolManager() as http:
        r = http.request('GET', url)
        with io.BytesIO(r.data) as f:
            reader = PyPDF2.PdfFileReader(f)
            nums = reader.getNumPages()
            print(type(nums), nums)
            for i in range(int(nums)):
                pageContent = ' '.join(reader.getPage(0).extractText().split('\n'))
                contents += pageContent
    # print(contents)
    return contents