异步爬取爱卡汽车论坛信息

一、获取论坛对应的汽车fid

import asyncio
import time
import aiohttp
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import json
import re

headers = {
    "Host": "www.xcar.com.cn",
    "Pragma": "no-cache",
    "Proxy-Connection": "keep-alive",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36"
}


res=requests.get(r"https://www.xcar.com.cn/bbs/",headers=headers)
html=res.content.decode(res.apparent_encoding)

soup=BeautifulSoup(html,'lxml')
span_list=soup.find_all("span",id="w959")
car_ids={}

for span in span_list:
    fid=re.findall("fid=(.*)",span.find("a").attrs.get('href'))[0]
    name=span.find("a").text
    car_ids[fid]=name

# 保存为本地json文件，方便后续使用
car_ids_str=json.dumps(car_ids,ensure_ascii=False)
with open("car.json", "w",encoding="utf-8") as f:
    f.write(car_ids_str)

二、asyncio爬取论坛信息

headers = {
    "Host": "www.xcar.com.cn",
    "Pragma": "no-cache",
    "Proxy-Connection": "keep-alive",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36"
}

with open("car.json", "rb") as f:
    car_ids = json.loads(f.read())

# 异步爬取函数
async def more_details(fid,page):
    _time=str(time.time()*1000)
    url = r"https://www.xcar.com.cn/bbs/xbbsapi/forumdisplay/get_thread_list.php"
    params = {
        "fid": fid,
        "orderby": "lastpost",
        "filter": "",
        "ondigest": "0",
        "page": page,
        "_": _time
    }
    async with aiohttp.ClientSession() as session:
        async with session.get(url=url, params=params,headers=headers) as resp:
            res=await resp.json(content_type='text/html',encoding='utf-8')
    return res

def run(car_name):
    for k, v in car_ids.items():
        if car_name in v:
            car_id = k
            # 创建异步循环事件池
            loop = asyncio.get_event_loop()
            # 使用ensure_future创建异步爬取任务task，最后通过result()来获取结果
            task=[asyncio.ensure_future(more_details(car_id,i)) for i in range(1,50)]
            done, _ =loop.run_until_complete(asyncio.wait(task))
            for t in done:
                res=t.result()
                print(res)
            loop.close()
run("奥迪A4L")