从 Python Azure 函数读取 Zip 文件的内容

Question

I have a Python HttpTrigger Azure Function that I am posting a Zip file to. The zip file contains a bunch of Excel files. I want to read the content of the Excel files, in memory, and discard the zip file (no need to persist it).

I tried the following:

<form enctype="multipart/form-data">
    <input name="file" type="file" />
    <input type="button" value="Upload" />
</form>

import logging

import azure.functions as func
import io
from zipfile import ZipFile
import pandas as pd

def extract_zip(content):
    with ZipFile(io.BytesIO(content)) as thezip:
        for zipinfo in thezip.infolist():
            with thezip.open(zipinfo) as thefile:
                yield zipinfo.filename, thefile

def main(req: func.HttpRequest) -> func.HttpResponse:
    logging.info('Python HTTP trigger function processed a request.')

    try:
        file=req.files.get('file')
        logging.info(file.filename)
        # I am trying at first to read one file, then I am going to do a for-loop
        for f_name, f_content in extract_zip(file):
            # Process the name and the Excel files content
        logging.info(file_name)

    except Exception as ex:
        logging.info(ex.args)

    return func.HttpResponse(f"the file {file.filename} upload successfully")

No matter what I try, I cannot read the content of the Excel, the name is coming as expected. What am I missing?

Answer 1

Below is a simply code to achieve that you need:

import logging

import azure.functions as func
import os
from zipfile import ZipFile
import pandas

def main(req: func.HttpRequest) -> func.HttpResponse:
    logging.info('Python HTTP trigger function processed a request.')
    out_file = open("test.zip", "wb") # open for [w]riting as [b]inary
    out_file.write(req.get_body())
    out_file.close()
    archive = ZipFile('test.zip','r')
    files = archive.namelist()
    for file in files:
        logging.info(file)
    book1 = archive.open('Book1.xlsx')
    df = pandas.read_excel(book1)
    #print the column names
    logging.info(df.columns)
    #get the values for a given column
    values = df['test1'].values
    logging.info(values)
    #get a data frame with selected columns
    FORMAT = ['test1', 'test2', 'test3']
    values_t = df[FORMAT].values
    logging.info(values_t)
    name = req.params.get('name')
    book1.close()
    archive.close()
    os.remove("test.zip")
    if not name:
        try:
            req_body = req.get_json()
        except ValueError:
            pass
        else:
            name = req_body.get('name')

    if name:
        return func.HttpResponse(f"Hello, {name}. This HTTP triggered function executed successfully.")
    else:
        return func.HttpResponse(
             "This HTTP triggered function executed successfully. Pass a name in the query string or in the request body for a personalized response.",
             status_code=200
        )

And you need to install pandas and xlrd, your requirement.txt file should be like this:

azure-functions
pandas
xlrd

This is the content of my .xlsx file:

And this is the result:

I can success get, please have a try on your side.