#!/usr/bin/python3
# coding=utf-8
import io
import sys
import time
import requests
import json
import re
import base64
from urllib.parse import urlparse, urljoin, quote
import urllib3
import gzip
import zlib
import brotli
import chardet
from typing import Optional, Tuple
# 禁用SSL警告
urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
SUC_RES = {
'resCode': 200,
'resTime': 0,
'keyword': 'SUCCESS',
'message': []
}
FAIL_RES = {
'resCode': 500,
'resTime': 0,
'keyword': 'FAILED',
'message': []
}
# 封装解码
class HttpResponseProcessor:
def __init__(self, url: str, headers: dict = None):
"""
初始化响应处理器
:param url: 请求的URL
:param headers: 请求头，默认为None
"""
self.url = url
self.headers = headers or {}
self.response = None
self.raw_content = None
self.text_content = None
self.encoding = None
self.status_code = None
def fetch_response(self):
"""
发送HTTP请求并获取响应
:return: None
"""
try:
self.response = requests.get(
url=self.url,
headers=self.headers,
allow_redirects=False, # 禁用自动重定向
stream=True # 流模式获取原始响应
)
self.status_code = self.response.status_code
self.raw_content = self.response.content
except Exception as e:
raise Exception(f"请求失败: {str(e)}")
def print_response_headers(self):
"""
打印响应头信息
:return: None
"""
if not self.response:
raise Exception("尚未获取响应，请先调用 fetch_response()")
print("=" * 50)
print("响应状态码:", self.status_code)
print("响应头信息:")
for key, value in self.response.headers.items():
print(f"{key}: {value}")
def decode_content(self) -> str:
"""
尝试解码内容为文本
:return: 解码后的文本内容
"""
if not self.raw_content:
raise Exception("尚未获取原始内容，请先调用 fetch_response()")
try:
# 检测内容编码
encoding_detected = chardet.detect(self.raw_content)['encoding']
#print(f"检测到的编码: {encoding_detected}")
# 尝试解码
if encoding_detected:
self.text_content = self.raw_content.decode(encoding_detected)
self.encoding = encoding_detected
else:
# 尝试常见编码
for encoding in ['utf-8', 'gbk', 'gb2312', 'latin1']:
try:
self.text_content = self.raw_content.decode(encoding)
self.encoding = encoding
print(f"成功使用 {encoding} 解码")
break
except:
continue
else:
self.text_content = "无法解码内容"
self.encoding = None
return self.text_content
except Exception as e:
print(f"解码失败: {str(e)}")
print("十六进制转储:")
# 打印前200字节的十六进制转储
hex_dump = ' '.join(f'{b:02x}' for b in self.raw_content[:200])
print(hex_dump)
# 将内容保存到文件以便分析
with open('response.bin', 'wb') as f:
f.write(self.raw_content)
print("已将响应内容保存为 'response.bin'")
raise Exception("内容解码失败")
def process_response(self) -> Tuple[int, Optional[str], Optional[str]]:
"""
完整处理响应的便捷方法
:return: (status_code, text_content, encoding)
"""
self.fetch_response()
self.print_response_headers()
text = self.decode_content()
return self.status_code, text, self.encoding
def print_err_result(e):
FAIL_RES['error'] = e
print(json.dumps(FAIL_RES, ensure_ascii=False))
exit(1)
def make_request(url, params=None, data=None, method='get', session=None):
try:
start = time.time()
req_func = session.get if session else requests.get
if method.lower() == 'post':
req_func = session.post if session else requests.post
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Accept': 'application/json,text/plain,text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
'X-Requested-With': 'XMLHttpRequest',
'accept-encoding': 'gzip, deflate, br,zstd'
}
response = req_func(
url,
params=params,
data=data,
verify=False,
headers=headers
)
res_time = (time.time() - start) * 1000
if response.status_code in [200, 302]:
SUC_RES['resTime'] = int(res_time)
SUC_RES['message'].append(f"请求 {url} 成功")
print(json.dumps(SUC_RES, ensure_ascii=False))
return response
else:
FAIL_RES['error'] = f"请求失败，状态码: {response.status_code}, 响应内容: {response.text},头信息：{session.headers}"
FAIL_RES['message'].append(f"请求 {url} 失败")
print(json.dumps(FAIL_RES, ensure_ascii=False))
return None
except Exception as e:
print_err_result(f"请求过程中发生错误: {str(e)}")
return None 详细解释下这段代码的含义
本文介绍如何使用json.dumps将Python字典转换为JSON格式，并保留中文字符。此外，还介绍了如何利用chardet库检测文件编码格式及获取系统默认编码的方法。
扫一扫
1万+
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
