spider【第六篇】并发爬虫

单线程爬虫

'''
cost time: 61s
'''
# coding=utf-8
import requests
from lxml import etree
import time


class QiuBai:
    def __init__(self):
        self.temp_url = "http://www.qiushibaike.com/text/page/{}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"}

    def get_url_list(self):
        return [self.temp_url.format(i) for i in range(1, 20)]

    def parse_url(self, url):
        print(url)
        response = requests.get(url, headers=self.headers)
        response.encoding = "utf-8"
        return response.text

    def get_content_list(self, html_str):  # 提取数据
        html_str = etree.HTML(html_str)
        div_list = html_str.xpath("//div[@id='content-left']/div")
        content_list = []
        for div in div_list:
            item = {}
            item["user_name"] = div.xpath(".//h2/text()")[0].strip()
            item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
            content_list.append(item)
        return content_list

    def save_content_list(self, content_list):  # 保存
        for content in content_list:
            print(content)

    def run(self):  # 实现做主要逻辑
        # 1. 准备url列表
        url_list = self.get_url_list()
        # 2. 遍历发送请求，获取响应
        for url in url_list:
            html_str = self.parse_url(url)
            # 3. 提取数据
            content_list = self.get_content_list(html_str)
            # 4. 保存
            self.save_content_list(content_list)


if __name__ == '__main__':
    t1 = time.time()
    qiubai = QiuBai()
    qiubai.run()
    print("total cost:", time.time() - t1)

v1

v1

多线程爬虫

把爬虫中的每个步骤封装成函数，分别用线程去执行
不同的函数通过队列相互通信，函数间解耦 

'''
cost time:  17s
'''
# coding=utf-8
import requests
from lxml import etree
from queue import Queue
import threading
import time


class QiuBai:
    def __init__(self):
        self.temp_url = "http://www.qiushibaike.com/text/page/{}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"}
        self.url_queue = Queue()
        self.html_queue = Queue()
        self.content_list_queue = Queue()

    def get_url_list(self):
        # return [self.temp_url.format(i) for i in range(1,14)]
        for i in range(1, 100):
            self.url_queue.put(self.temp_url.format(i))

    def parse_url(self):
        while True:
            url = self.url_queue.get()
            response = requests.get(url, headers=self.headers)
            response.encoding = "utf-8"
            print(response.text)

            if response.status_code != 200:
                self.url_queue.put(url)
            else:
                self.html_queue.put(response.content.decode())
            self.url_queue.task_done()  # 让队列的计数-1

    def get_content_list(self):  # 提取数据
        while True:
            html_str = self.html_queue.get()
            html = etree.HTML(html_str)
            div_list = html.xpath("//div[@id='content-left']/div")
            content_list = []
            for div in div_list:
                item = {}
                item["user_name"] = div.xpath(".//h2/text()")[0].strip()
                item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
                content_list.append(item)
            self.content_list_queue.put(content_list)
            self.html_queue.task_done()

    def save_content_list(self):  # 保存
        while True:
            content_list = self.content_list_queue.get()
            for content in content_list:
                # print(content)
                pass
            self.content_list_queue.task_done()

    def run(self):  # 实现做主要逻辑
        thread_list = []
        # 1. 准备url列表
        t_url = threading.Thread(target=self.get_url_list)
        thread_list.append(t_url)
        # 2. 遍历发送请求，获取响应
        for i in range(3):
            t_parse = threading.Thread(target=self.parse_url)
            thread_list.append(t_parse)
        # 3. 提取数据
        t_content = threading.Thread(target=self.get_content_list)
        thread_list.append(t_content)
        # 4. 保存
        t_save = threading.Thread(target=self.save_content_list)
        thread_list.append(t_save)

        for t in thread_list:
            t.setDaemon(True)  # 把子线程设置为守护线程
            t.start()

        for q in [self.url_queue, self.html_queue, self.content_list_queue]:
            q.join()  # 让主线程阻塞，等待队列计数为0


if __name__ == '__main__':
    t1 = time.time()
    qiubai = QiuBai()
    qiubai.run()
    print("total cost:", time.time() - t1)

v2

# coding=utf-8
import requests
from lxml import etree
import time
from queue import Queue
from multiprocessing.dummy import Pool


class QiuBai:
    def __init__(self):
        self.temp_url = "http://www.qiushibaike.com/text/page/{}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"}
        self.queue = Queue()
        self.pool = Pool(5)
        self.is_running = True
        self.total_request_num = 0
        self.total_response_num = 0
        self.proxies = {"http": "http://58.247.179.94:8060"}

    def get_url_list(self):
        for i in range(1, 14):
            self.queue.put(self.temp_url.format(i))
            self.total_request_num += 1

    def parse_url(self, url):
        # response = requests.get(url,headers=self.headers,proxies=self.proxies)
        response = requests.get(url, headers=self.headers)
        print(response)
        return response.content.decode()

    def get_content_list(self, html_str):  # 提取数据
        html = etree.HTML(html_str)
        div_list = html.xpath("//div[@id='content-left']/div")
        content_list = []
        for div in div_list:
            item = {}
            item["user_name"] = div.xpath(".//h2/text()")[0].strip()
            item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
            content_list.append(item)
        return content_list

    def save_content_list(self, content_list):  # 保存
        for content in content_list:
            # print(content)
            pass

    def _execete_request_content_save(self):  # 进行一次url地址的请求，提取，保存
        url = self.queue.get()
        html_str = self.parse_url(url)
        # 3. 提取数据
        content_list = self.get_content_list(html_str)
        # 4. 保存
        self.save_content_list(content_list)
        self.total_response_num += 1

    def _callback(self, temp):
        if self.is_running:
            self.pool.apply_async(self._execete_request_content_save, callback=self._callback)

    def run(self):  # 实现做主要逻辑
        # 1. 准备url列表
        self.get_url_list()
        for i in range(3):  # 设置并发数为3
            self.pool.apply_async(self._execete_request_content_save, callback=self._callback)

        while True:
            time.sleep(0.0001)
            if self.total_response_num >= self.total_request_num:
                self.is_running = False
                break


if __name__ == '__main__':
    t1 = time.time()
    qiubai = QiuBai()
    qiubai.run()
    print("total cost:", time.time() - t1)

v2.2 线程池

多进程爬虫

# coding=utf-8
import requests
from lxml import etree
# from queue import Queue
# import threading
from multiprocessing import Process
from multiprocessing import JoinableQueue as Queue
import time


class QiuBai:
    def __init__(self):
        self.temp_url = "http://www.qiushibaike.com/text/page/{}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"}
        self.url_queue = Queue()
        self.html_queue = Queue()
        self.content_list_queue = Queue()
        self.proxies = None # {"http": "http://58.247.179.94:8060"}

    def get_url_list(self):
        # return [self.temp_url.format(i) for i in range(1,14)]
        for i in range(1, 14):
            self.url_queue.put(self.temp_url.format(i))

    def parse_url(self):
        while True:
            url = self.url_queue.get()
            response = requests.get(url, headers=self.headers, proxies=self.proxies)
            print(response)

            if response.status_code != 200:
                self.url_queue.put(url)
            else:
                self.html_queue.put(response.content.decode())
            self.url_queue.task_done()  # 让队列的计数-1

    def get_content_list(self):  # 提取数据
        while True:
            html_str = self.html_queue.get()
            html = etree.HTML(html_str)
            div_list = html.xpath("//div[@id='content-left']/div")
            content_list = []
            for div in div_list:
                item = {}
                item["user_name"] = div.xpath(".//h2/text()")[0].strip()
                item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
                content_list.append(item)
            self.content_list_queue.put(content_list)
            self.html_queue.task_done()

    def save_content_list(self):  # 保存
        while True:
            content_list = self.content_list_queue.get()
            for content in content_list:
                # print(content)
                pass
            self.content_list_queue.task_done()

    def run(self):  # 实现做主要逻辑
        thread_list = []
        # 1. 准备url列表
        t_url = Process(target=self.get_url_list)
        thread_list.append(t_url)
        # 2. 遍历发送请求，获取响应
        for i in range(13):
            t_parse = Process(target=self.parse_url)
            thread_list.append(t_parse)
        # 3. 提取数据
        t_content = Process(target=self.get_content_list)
        thread_list.append(t_content)
        # 4. 保存
        t_save = Process(target=self.save_content_list)
        thread_list.append(t_save)

        for process in thread_list:
            process.daemon = True  # 把子线程设置为守护线程
            process.start()

        for q in [self.url_queue, self.html_queue, self.content_list_queue]:
            q.join()  # 让主线程阻塞，等待队列计数为0


if __name__ == '__main__':
    t1 = time.time()
    qiubai = QiuBai()
    qiubai.run()
    print("total cost:", time.time() - t1)

v3

协程爬虫

# coding=utf-8
import gevent.monkey

gevent.monkey.patch_all()

from gevent.pool import Pool
import requests
from lxml import etree
import time
from queue import Queue


class QiuBai:
    def __init__(self):
        self.temp_url = "http://www.qiushibaike.com/text/page/{}"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"}
        self.queue = Queue()
        self.pool = Pool(5)
        self.is_running = True
        self.total_request_num = 0
        self.total_response_num = 0
        self.proxies = {"http": "http://58.247.179.94:8060"}

    def get_url_list(self):
        for i in range(1, 14):
            self.queue.put(self.temp_url.format(i))
            self.total_request_num += 1

    def parse_url(self, url):
        # response = requests.get(url,headers=self.headers,proxies=self.proxies)
        response = requests.get(url, headers=self.headers)
        return response.content.decode()

    def get_content_list(self, html_str):  # 提取数据
        html = etree.HTML(html_str)
        div_list = html.xpath("//div[@id='content-left']/div")
        content_list = []
        for div in div_list:
            item = {}
            item["user_name"] = div.xpath(".//h2/text()")[0].strip()
            item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
            content_list.append(item)
        return content_list

    def save_content_list(self, content_list):  # 保存
        for content in content_list:
            print(content)
            pass

    def _execete_request_content_save(self):  # 进行一次url地址的请求，提取，保存
        url = self.queue.get()
        html_str = self.parse_url(url)
        # 3. 提取数据
        content_list = self.get_content_list(html_str)
        # 4. 保存
        self.save_content_list(content_list)
        self.total_response_num += 1

    def _callback(self, temp):
        if self.is_running:
            self.pool.apply_async(self._execete_request_content_save, callback=self._callback)

    def run(self):  # 实现做主要逻辑
        # 1. 准备url列表
        self.get_url_list()
        for i in range(3):  # 设置并发数为3
            self.pool.apply_async(self._execete_request_content_save, callback=self._callback)

        while True:
            time.sleep(0.0001)
            if self.total_response_num >= self.total_request_num:
                self.is_running = False
                break


if __name__ == '__main__':
    t1 = time.time()
    qiubai = QiuBai()
    qiubai.run()
    print("total cost:", time.time() - t1)

v4

 

转载于:https://www.cnblogs.com/hyit/articles/10692936.html