本文主要介绍Python中,解析获取curl命令行参数字符串,并且将获取到的参数转换成字典(Dictionary)方法,以及相关的示例代码。

1、curl示例命令及参数

  curl_command = (
            "curl 'http://httpbin.org/post' -X POST -H 'Cookie: _gauges_unique"
            "_year=1; _gauges_unique=1; _gauges_unique_month=1; _gauges_unique"
            "_hour=1; _gauges_unique_day=1' -H 'Origin: http://httpbin.org' -H"
            " 'Accept-Encoding: gzip, deflate' -H 'Accept-Language: en-US,en;q"
            "=0.9,ru;q=0.8,es;q=0.7' -H 'Upgrade-Insecure-Requests: 1' -H 'Use"
            "r-Agent: Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTM"
            "L, like Gecko) Ubuntu Chromium/62.0.3202.75 Chrome/62.0.3202.75 S"
            "afari/537.36' -H 'Content-Type: application/x-www-form-urlencoded"
            "' -H 'Accept: text/html,application/xhtml+xml,application/xml;q=0"
            ".9,image/webp,image/apng,*/*;q=0.8' -H 'Cache-Control: max-age=0'"
            " -H 'Referer: http://httpbin.org/forms/post' -H 'Connection: keep"
            "-alive' --data 'custname=John+Smith&custtel=500&custemail=jsmith%"
            "40example.org&size=small&topping=cheese&topping=onion&delivery=12"
            "%3A15&comments=' --compressed"
        )

2、获取解析curl命令行字符串及转换字典(Dictionary)代码

安装引用w3lib

pip install w3lib

示例代码是针对curl命令的,如果需要获取解析其它命令字符串,也可以参考如下代码:

import argparse
import warnings
from shlex import split
from http.cookies import SimpleCookie
from urllib.parse import urlparse
from w3lib.http import basic_auth_header

class CurlParser(argparse.ArgumentParser):
    def error(self, message):
        error_msg = \
            'There was an error parsing the curl command: {}'.format(message)
        raise ValueError(error_msg)

curl_parser = CurlParser()
curl_parser.add_argument('url')
curl_parser.add_argument('-H', '--header', dest='headers', action='append')
curl_parser.add_argument('-X', '--request', dest='method', default='get')
curl_parser.add_argument('-d', '--data', dest='data')
curl_parser.add_argument('-u', '--user', dest='auth')

safe_to_ignore_arguments = [
    ['--compressed'],
    # `--compressed` argument is not safe to ignore, but it's included here
    # because the `HttpCompressionMiddleware` is enabled by default
    ['-s', '--silent'],
    ['-v', '--verbose'],
    ['-#', '--progress-bar']
]
for argument in safe_to_ignore_arguments:
    curl_parser.add_argument(*argument, action='store_true')

def curl_to_request_kwargs(curl_command, ignore_unknown_options=True):
    """Convert a cURL command syntax to Request kwargs.
    :param str curl_command: string containing the curl command
    :param bool ignore_unknown_options: If true, only a warning is emitted when
    cURL options are unknown. Otherwise raises an error. (default: True)
    :return: dictionary of Request kwargs
    """
    curl_args = split(curl_command)
    if curl_args[0] != 'curl':
        raise ValueError('A curl command must start with "curl"')
    parsed_args, argv = curl_parser.parse_known_args(curl_args[1:])
    if argv:
        msg = 'Unrecognized options: {}'.format(', '.join(argv))
        if ignore_unknown_options:
            warnings.warn(msg)
        else:
            raise ValueError(msg)
    url = parsed_args.url
    # curl automatically prepends 'http' if the scheme is missing, but Request
    # needs the scheme to work
    parsed_url = urlparse(url)
    if not parsed_url.scheme:
        url = 'http://' + url
    result = {'method': parsed_args.method.upper(), 'url': url}
    headers = []
    cookies = {}
    for header in parsed_args.headers or ():
        name, val = header.split(':', 1)
        name = name.strip()
        val = val.strip()
        if name.title() == 'Cookie':
            for name, morsel in SimpleCookie(val).items():
                cookies[name] = morsel.value
        else:
            headers.append((name, val))
    if parsed_args.auth:
        user, password = parsed_args.auth.split(':', 1)
        headers.append(('Authorization', basic_auth_header(user, password)))
    if headers:
        result['headers'] = headers
    if cookies:
        result['cookies'] = cookies
    if parsed_args.data:
        result['body'] = parsed_args.data
    return result

调用方法:

import curl_to_request_kwargs
#忽略未知参数
result = curl_to_request_kwargs(curl_command)
#不忽略未知参数
result = curl_to_request_kwargs(curl_command,False)


推荐文档