Python爬虫之使用celery加速爬虫

其中，app_test.py为主程序，其代码如下：

from celery import Celery

app = Celery('proj', include=['proj.tasks'])
app.config_from_object('proj.celeryconfig')

if __name__ == '__main__':
    app.start()

tasks.py为任务函数，代码如下：

import re
import requests
from celery import group
from proj.app_test import app

@app.task(trail=True)
# 并行调用任务
def get_content(urls):
    return group(C.s(url) for url in urls)()

@app.task(trail=True)
def C(url):
    return parser.delay(url)

@app.task(trail=True)
# 获取每个网页的name和description
def parser(url):
    req = requests.get(url)
    html = req.text
    try:
        name = re.findall(r'<span class="wikibase-title-label">(.+?)</span>', html)[0]
        desc = re.findall(r'<span class="wikibase-descriptionview-text">(.+?)</span>', html)[0]
        if name is not None and desc is not None:
            return name, desc
    except Exception as  err:
        return '', ''

celeryconfig.py为celery的配置文件，代码如下：

BROKER_URL = 'redis://localhost' # 使用Redis作为消息代理

CELERY_RESULT_BACKEND = 'redis://localhost:6379/0' # 把任务结果存在了Redis

CELERY_TASK_SERIALIZER = 'msgpack' # 任务序列化和反序列化使用msgpack方案

CELERY_RESULT_SERIALIZER = 'json' # 读取任务结果一般性能要求不高，所以使用了可读性更好的JSON

CELERY_TASK_RESULT_EXPIRES = 60 * 60 * 24 # 任务过期时间

CELERY_ACCEPT_CONTENT = ['json', 'msgpack'] # 指定接受的内容类型

最后是我们的爬虫文件，scrapy.py，代码如下：

import time
import requests
from bs4 import BeautifulSoup
from proj.tasks import get_content

t1 = time.time()

url = 
# 请求头部
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, \
            like Gecko) Chrome/67.0.3396.87 Safari/537.36'}
# 发送HTTP请求
req = requests.get(url, headers=headers)
# 解析网页
soup = BeautifulSoup(req.text, "lxml")
# 找到name和Description所在的记录
human_list = soup.find(id='mw-whatlinkshere-list')('li')

urls = []
# 获取网址
for human in human_list:
    url = human.find('a')['href']
    

#print(urls)

# 调用get_content函数，并获取爬虫结果
result = get_content.delay(urls)

res = [v for v in result.collect()]

for r in res:
    if isinstance(r[1], list) and isinstance(r[1][0], str):
        print(r[1])


t2 = time.time() # 结束时间
print('耗时：%s' % (t2 - t1))

  在后台启动redis，并切换至proj项目所在目录，运行命令：

celery -A proj.app_test worker -l info

输出结果如下(只显示最后几行的输出)：

......
['Antoine de Saint-Exupery', 'French writer and aviator']
['', '']
['Sir John Barrow, 1st Baronet', 'English statesman']
['Amy Johnson', 'pioneering English aviator']
['Mike Oldfield', 'English musician, multi-instrumentalist']
['Willoughby Newton', 'politician from Virginia, USA']
['Mack Wilberg', 'American conductor']
耗时：80.05160284042358

在rdm中查看数据，如下：