几乎一样的代码和配置, aiohttp 和 requests 获取到的页面内容不一样, 这个问题可能出在哪?

查了一下 Stack Overflow 问题可能在 ssl 上, 但是改了还是不行。

import asyncio
import requests
import time
import json
import random
import aiohttp
from ori_async import get_proxy

list_url = 'https://www.amazon.co.uk/s?k=dress&ref=nb_sb_noss'
product_url = 'https://www.amazon.co.uk/AUSELILY-Womens-Sleeve-Pleated-Pockets/dp/B082W811L3/ref=sr_1_1_sspa?dchild=1&keywords=dress&qid=1596264150&s=clothing&sr=1-1-spons&psc=1&spLa=ZW5jcnlwdGVkUXVhbGlmaWVyPUEzTEpRR0NLRlhQMFFDJmVuY3J5cHRlZElkPUEwMDY5Nzg5MkZTUllZWTM3VFVIQiZlbmNyeXB0ZWRBZElkPUEwOTU0NzQ1MTE0QzhFV0w0SjJOMCZ3aWRnZXROYW1lPXNwX2F0ZiZhY3Rpb249Y2xpY2tSZWRpcmVjdCZkb05vdExvZ0NsaWNrPXRydWU='
baidu_url = 'https://www.baidu.com'


headers = {
        "authority": "www.amazon.co.uk",
        "method": "GET",
        "path": "/s?k=dress&i=clothing&ref=nb_sb_noss",
        "scheme": "https",
        "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
        "accept-encoding": "gzip, deflate, br",
        "accept-language": "zh-CN,zh;q=0.9,en;q=0.8,en-US;q=0.7,ja;q=0.6,zh-TW;q=0.5",
        "cache-control": "max-age=0",
        "cookie": "session-id=258-7467381-0898317; i18n-prefs=GBP; ubid-acbuk=262-6045121-6110346; x-wl-uid=13CgqXYwZCFN3okL9HYQm7Iyt8Md2S5Dj4uA/dwKZrgtM0V8Ii0/OTO/AbtTOSRVzmlpbyCfIvZw=; session-token=\"K1UgAkfjQLKORhX6CN0AXXcRycoGecW5zqC3Nk8y/0rr7ZHQPpm5kzjT0YPAY/M8vVOWYNXoWCDYhSbrXyHP/bnNILWcLd2I+04dfUASNtpMHQkTh2YNffN748Rd9HxMQ6wFjVkDsfhgbm/YgEQ5uy8H+qWM1i9z+8uePKVL1BfVQtQpOEFxLQK+1GRQHBfdt7urN81Bkg0WjHz3pOVR31pILIjf3aM1nhncWG1P/A93yPpUOBTFeMh5/6V4RrddfHGn4uifWdg=\"; session-id-time=2082758401l; csm-hit=tb:3GP38DER2C68WEEPMTK8+s-KCAYBB85E78WBDWP92X7|1595834228498&t:1595834228498&adb:adblk_yes",
        "downlink": "9.75",
        "ect": "4g",
        "rtt": "200",
        "sec-fetch-dest": "document",
        "sec-fetch-mode": "navigate",
        "sec-fetch-site": "same-origin",
        "sec-fetch-user": "?1",
        "upgrade-insecure-requests": "1",
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4181.9 Safari/537.36"
}
url = list_url
# proxies = get_proxy()
async def main():
    connector = aiohttp.TCPConnector(ssl=False)
    async with aiohttp.ClientSession(connector=connector) as session:
        async with session.get(url, headers=data["headers"]) as resp:
            print(resp.status)
            content = await resp.text()
            print(len(content))

start = time.time()
loop = asyncio.get_event_loop()
loop.run_until_complete(main())
end = time.time()
print('spend time is {}'.format(end - start))

# response = requests.get(url, headers=headers, proxies=proxies, timeout=8, verify=False)
response = requests.get(url, headers=headers, timeout=8, verify=False)
print("length is {}".format(len(response.text)))

locoz

2020-08-03 11:36:30 +08:00

@woshichuanqilz #2
aiohttp 的请求在抓包工具里不显示大概是因为你根本没有设置让它走代理，在请求的时候带上 proxy 参数就行了。

抓包先看 HTTP 层的各个参数有没有区别，有的话先处理成一模一样的。aiohttp 和 requests 的实现不同，对一些情况的处理并不相同，比如常见容易出问题的情况是 headers 里多了东西或者少了东西，或者是某个有特殊符号之类的 value 被编码成另一种样子之类的。
如果 HTTP 层都统一了但还是有区别的话，就用 wireshark 看看 SSL 层有没有什么区别，比如常见用来做 SSL 指纹的加密套件部分。