多组建的pipline技术架构

生产者消费者爬虫的架构

多进程数据通信的queue.Queue

线程安全：指的是多个线程不会冲突
get和put方法是阻塞的：当里面没有数据的时候，q.get()会卡住，直到里面有了数据把它取出来，q.put()当队列满了以后会卡住，直到有一个空闲的位置才能put进去

代码实现

tmp/blog_spider.py

import requests
from bs4 import BeautifulSoup

urls = [
    f"https://www.cnblogs.com/#p{page}"
    for page in range(1, 50+1)
]

def craw(url):
    r = requests.get(url)
    return r.text

def parse(html):
    soup = BeautifulSoup(html, 'html.parser')
    links = soup.find_all("a", class_="post-item-title")
    return [(link["href"], link.get_text()) for link in links]


if __name__ == '__main__':
    for result in parse(craw(urls[2])):
        print(result)

tmp/02.producer_consumer_spider.py

import queue
import blog_spider
import time, random
import threading


#生产者
def do_craw(url_queue: queue.Queue, html_queue: queue.Queue):
    while True:
        url = url_queue.get()
        html = blog_spider.craw(url)
        html_queue.put(html)
        print(threading.current_thread().name + f" craw {url}",
              "url_queue.size=", url_queue.qsize())
        time.sleep(random.randint(1, 2))

#消费者
def do_parse(html_queue: queue.Queue, fout):
    while True:
        html = html_queue.get()
        results = blog_spider.parse(html)
        for result in results:
            fout.write(str(result) + "\n")
        print(threading.current_thread().name + " results.size", len(results),
              "html_queue.size=", html_queue.qsize())
        time.sleep(random.randint(1, 2))



if __name__ == '__main__':
    url_queue = queue.Queue()
    html_queue = queue.Queue()
    for url in blog_spider.urls:
        url_queue.put(url)

    for idx in range(3):
        t = threading.Thread(target=do_craw, args=(url_queue, html_queue),
                             name=f"craw{idx}")
        t.start()


    fout = open("02.data.txt", "w")
    for idx in range(2):
        t = threading.Thread(target=do_parse, args=(html_queue, fout),
                             name=f"parse{idx}")
        t.start()

爬取结果