Python异步爬取知乎热榜实例分享

一、错误代码：摘要和详细的url获取不到

import asyncio
from bs4 import BeautifulSoup
import aiohttp
 
headers={
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
    'referer': 'https://www.baidu.com/s?tn=02003390_43_hao_pg&isource=infinity&iname=baidu&itype=web&ie=utf-8&wd=％E7％9F％A5％E4％B9％8E％E7％83％AD％E6％A6％9C'
}
async def getPages(url):
    async with aiohttp.ClientSession(headers=headers) as session:
        async with session.get(url) as resp:
            print(resp.status)  # 打印状态码
            html=await resp.text()
    soup=BeautifulSoup(html,'lxml')
    items=soup.select('.HotList-item')
    for item in items:
        title=item.select('.HotList-itemTitle')[0].text
        try:
            abstract=item.select('.HotList-itemExcerpt')[0].text
        except:
            abstract='No Abstract'
        hot=item.select('.HotList-itemMetrics')[0].text
        try:
            img=item.select('.HotList-itemImgContainer img')['src']
        except:
            img='No Img'
        print("{}\n{}\n{}".format(title,abstract,img))
 
if __name__ == '__main__':
    url='https://www.zhihu.com/billboard'
    loop=asyncio.get_event_loop()
    loop.run_until_complete(getPages(url))
    loop.close()

二、查看JS代码

发现详细链接、图片链接、问题摘要等都在JS里面（CSDN的开发者助手插件确实好用）

正则表达式获取上述信息:

接下来就是详细的代码啦

import asyncio
import json
import re
import aiohttp
 
headers={
    'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36',
    'referer': 'https://www.baidu.com/s?tn=02003390_43_hao_pg&isource=infinity&iname=baidu&itype=web&ie=utf-8&wd=％E7％9F％A5％E4％B9％8E％E7％83％AD％E6％A6％9C'
}
async def getPages(url):
    async with aiohttp.ClientSession(headers=headers) as session:
        async with session.get(url) as resp:
            print(resp.status)  # 打印状态码
            html=await resp.text()
 
    regex=re.compile('"hotList":(.*?),"guestFeeds":')
    text=regex.search(html).group(1)
    # print(json.loads(text))   # json换成字典格式
    for item in json.loads(text):
        title=item['target']['titleArea']['text']
        question=item['target']['excerptArea']['text']
        hot=item['target']['metricsArea']['text']
        link=item['target']['link']['url']
        img=item['target']['imageArea']['url']
        if not img:
            img='No Img'
        if not question:
            question='No Abstract'
        print("Title：{}\nPopular：{}\nQuestion：{}\nLink：{}\nImg：{}".format(title,hot,question,link,img))
 
if __name__ == '__main__':
    url='https://www.zhihu.com/billboard'
    loop=asyncio.get_event_loop()
    loop.run_until_complete(getPages(url))
    loop.close()

来源：https://kantlee.blog.csdn.net/article/details/113665084