Python 的七个HTTP请求库对比小结

curl ^"https://movie.douban.com/j/chart/top_list_count?type=11&interval_id=100^%^3A90&action=^"  ^
  -H "Accept: */*" ^
  -H "Accept-Language: zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7" ^
  -H "Connection: keep-alive" ^
  -H ^"Cookie: ll=^\^"118282^\^"; bid=p6VTwxlhQxU; _pk_id.100001.4cf6=1960560bd6f348cf.1717555113.; __utmc=30149280; __utmc=223695111; __yadk_uid=vu9yRywnfgofYdkNxlDGN1LGZumZZlP3; _vwo_uuid_v2=DB54A160968C09D586B65593E774AC10A^|93b3f99adf2e8bfe6ce4a84c068e3f82; _pk_ref.100001.4cf6=^%^5B^%^22^%^22^%^2C^%^22^%^22^%^2C1717727676^%^2C^%^22https^%^3A^%^2F^%^2Fwww.heywhale.com^%^2F^%^22^%^5D; push_noty_num=0; push_doumail_num=0; __utmv=30149280.19806; __utma=30149280.912128761.1717555113.1717725025.1717728345.3; __utmz=30149280.1717728345.3.2.utmcsr=google^|utmccn=(organic)^|utmcmd=organic^|utmctr=(not^%^20provided); __utma=223695111.1475293929.1717555113.1717727676.1717728345.4; __utmz=223695111.1717728345.4.2.utmcsr=google^|utmccn=(organic)^|utmcmd=organic^|utmctr=(not^%^20provided)^" ^
  -H ^"Referer: https://movie.douban.com/typerank?type_name=^%^E5^%^89^%^A7^%^E6^%^83^%^85&type=11&interval_id=100:90&action=^"  ^
  -H "Sec-Fetch-Dest: empty" ^
  -H "Sec-Fetch-Mode: cors" ^
  -H "Sec-Fetch-Site: same-origin" ^
  -H "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36" ^
  -H "X-Requested-With: XMLHttpRequest" ^
  -H ^"sec-ch-ua: ^\^"Google Chrome^\^";v=^\^"125^\^", ^\^"Chromium^\^";v=^\^"125^\^", ^\^"Not.A/Brand^\^";v=^\^"24^\^"^" ^
  -H "sec-ch-ua-mobile: ?0" ^
  -H ^"sec-ch-ua-platform: ^\^"Windows^\^"^"

import requests

url = "https://movie.douban.com/j/chart/top_list_count?type=11&interval_id=100:90&action="
headers = {
    "Accept": "*/*",
    "Accept-Language": "zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7",
    "Connection": "keep-alive",
    # Cookie 头过长，需要按实际值填充
    # ...
    "Referer": "https://movie.douban.com/typerank?type_name=剧情&type=11&interval_id=100:90&action=",
    # 其他 headers 按需填充
    # ...
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36"
}

response = requests.get(url, headers=headers)
print(response.text)

import aiohttp
import asyncio

async def fetch(url, headers):
    async with aiohttp.ClientSession() as session:
        async with session.get(url, headers=headers) as response:
            return await response.text()

url = "https://movie.douban.com/j/chart/top_list_count?type=11&interval_id=100:90&action="
headers = {...}  # 同上

loop = asyncio.get_event_loop()
html = loop.run_until_complete(fetch(url, headers))
print(html)

import http.client
import urllib.parse

conn = http.client.HTTPSConnection("movie.douban.com")

# 将参数编码为URL
params = urllib.parse.urlencode({
    'type': '11',
    'interval_id': '100:90',
    'action': ''
})
url = f"/j/chart/top_list_count?{params}"

headers = {
    # 同上
}

conn.request("GET", url, headers=headers)

response = conn.getresponse()
data = response.read()

print(data.decode('utf-8'))

conn.close()