Python多进程批量爬取小说代码分享

#!/usr/bin/env python# -*- coding: utf-8 -*-# @Time    : 2019/1/3 17:15# @Author  : jia.zhao# @Desc    :# @File    : process_spider.py# @Software: PyCharmfrom multiprocessing import Process, Lock, Queueimport timefrom selenium import webdriverfrom selenium.webdriver.chrome.options import Optionsimport requestsfrom lxml import etreeexitFlag = 0q = Queue()chrome_options = Options()chrome_options.add_argument('--headless')class scrapy_biquge():    def get_url(self):        browser = webdriver.Chrome(chrome_options=chrome_options)        browser.get('http://www.xbiquge.la/xuanhuanxiaoshuo/')        # 获取小说        content = browser.find_element_by_class_name("r")        content = content.find_elements_by_xpath('//ul/li/span[@class="s2"]/a')        for i in range(len(content)):            # 小说名字            title = content[i].text            # 小说的url            href = content[i].get_attribute('href')            print(title + '+' + href)            # 装进队列            q.put(title + '+' + href)            if i == 3:                break        browser.close()        browser.quit()def get_dir(title, href):    time.sleep(2)    res = requests.get(href, timeout=60)    res.encoding = 'utf8'    novel_contents = etree.HTML(res.text)    novel_dir = novel_contents.xpath('//div[@id="list"]/dl/dd/a//text()')    novel_dir_href = novel_contents.xpath('//div[@id="list"]/dl/dd/a/@href')    path = 'novel/' + title + '.txt'    list_content = []    i = 0    for novel in range(len(novel_dir)):        novel_dir_content = get_content('http://www.xbiquge.la'+novel_dir_href[novel])        print(title, novel_dir[novel])        list_content.append(novel_dir[novel] + '\n' + ''.join(novel_dir_content) + '\n')        i = i + 1        if i == 2:            try:                with open(path, 'a', encoding='utf8') as f:                    f.write('\n'.join(list_content))                    f.close()                list_content = []                i = 0            except Exception as e:                print(e)def get_content(novel_dir_href):    time.sleep(2)    res = requests.get(novel_dir_href, timeout=60)    res.encoding = 'utf8'    html_contents = etree.HTML(res.text)    novel_dir_content = html_contents.xpath('//div[@id="content"]//text()')    return novel_dir_contentclass MyProcess(Process):    def __init__(self, q, lock):        Process.__init__(self)        self.q = q        self.lock = lock    def run(self):        print(self.q.qsize(), '队列大小')        print('Pid: ' + str(self.pid) + ' LoopCount: ')        self.lock.acquire()        while not self.q.empty():            item = self.q.get()            print(item)            self.lock.release()            title = item.split('+')[0]            href = item.split('+')[1]            try:                get_dir(title, href)            except Exception as e:                print(e, '出现异常跳过循环')                continueif __name__ == '__main__':    start_time = time.time()    print(start_time)    scrapy_biquge().get_url()    lock = Lock()    p0 = MyProcess(q, lock)    p0.start()    p1 = MyProcess(q, lock)    p1.start()    p2 = MyProcess(q, lock)    p2.start()    p3 = MyProcess(q, lock)    p3.start()    p0.join()    p1.join()    p2.join()    p3.join()    end_time = time.time()    print(start_time, end_time, end_time - start_time, '时间差')

使用多进程中的队列处理，实现进程间数据共享。代码应该可以直接运行，有问题可以留言