好久没写过爬虫了,今天看到有群友在问就看了下他的代码,大概是一个异步的爬取影视作品链接的爬虫,看到有别的大佬给他解决了问题后他发了张存入mongodb的截图,于是我也正好学习也复习下asyncio。
motor
Motor 提供了一个基于协程的 API,用于从Tornado或asyncio对 MongoDB 的非阻塞访问。Motor 在连接到 MongoDB 或执行 I/O 时从不阻塞事件循环。Motor 封装了几乎所有 PyMongo 的 API 并使其成为非阻塞的。
代码
import re
import asyncio
import aiohttp
from lxml import etree
import motor.motor_asyncio
client = motor.motor_asyncio.AsyncIOMotorClient()
collection = client.film.kkxz_test
async def index_page(url):
page_url_list = []
async with aiohttp.ClientSession() as session:
async with session.get(url) as req:
res = await req.json()
for page_url in res['data']:
page_url_list.append('https://kkxz.vip/d/' + page_url['attributes']['slug'])
await save_data(page_url_list)
async def save_data(urls):
for url in urls:
async with aiohttp.ClientSession() as session:
async with session.get(url) as req:
text = await req.text()
movie_link = re.findall('href="(https://pan.quark.cn.*?)"', text)
movie_title = re.findall('<h2>(.*?)</h2>', text)
print(movie_title[0], movie_link)
await collection.insert_one({'title': movie_title[0],'link': movie_link})
async def main():
url = 'https://kkxz.vip/api/discussions?include=user%2ClastPostedUser%2CfirstPost%2Ctags%2Ctags.parent&filter%5Btag%5D=tv&sort&page%5Boffset%5D={id}'
tasks = [asyncio.create_task(index_page(url.format(id = i))) for i in range(0, 20, 30)]
await asyncio.wait(tasks)
if __name__ == '__main__':
asyncio.run(main())