多进程爬取猫眼电影TOP100的电影数据

崔庆才 Python3爬虫入门到精通课程视频练习

利用多进程和re 爬取猫眼电影TOP100的电影数据

爬虫与数据分析：Github
代码如下：

# -*- coding:utf-8 -*-
import requests
import re
import json
from multiprocessing import Pool



def get_one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.117 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    if response.status_code == 200:
        return response.text
    return None


import pandas as pd

def parse_one_page(html):
    pattern = re.compile(
        '<dd>.*?board-index.*?>(.*?)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>(.*?)</i>.*?fraction.*?>(.*?)</i>.*?</dd>',
        re.S)
    items = re.findall(pattern, html)
    #print(items)
    content = []
    for item in items:
        dataset = {}
        dataset['index']=item[0]
        print(dataset['index'])
        dataset['image']=item[1]
        dataset['title']=item[2].strip()
        dataset['actor']=item[3].strip()[3:] if len(item[3]) > 3 else ''
        dataset['time'] =item[4].strip()[5:] if len(item[4]) > 5 else ''
        dataset['score']=item[5].strip() + item[6].strip()
        content.append(dataset)
    return content



def write_to_file(content):
    df = pd.DataFrame(content)
    #print(df.index)
    df.to_csv('maoyan.csv',index=False,mode='a+')

def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    data=parse_one_page(html)
    write_to_file(data)

import time
if __name__ == '__main__':

    start=time.time()
    pool=Pool()

    pool.map(main,[i*10 for i in range(10)])
    # for i in range(10):
    #     main(offset=i * 10)

    print('花费时间:',time.time()-start)

多线程
一般通过两种方式实现多线程，
第一种方式是把一个函数传入并创建实例，然后调用start方法执行；
第二种方式是直接从threading.Thread继承并创建线程类，然后重写_init_方法和run方法。

import time
import random
import threading

def t_run(urls):
    """
    线程执行代码
    """
    # threading.current_thread()返回当前的Thread对象，对应于调用者控制的线程。
    # 如果调用者控制的线程不是通过threading模块创建的，则返回一个只有有限功能的虚假线程对象。
    print('Current %s is running...' % threading.current_thread().name)
    for url in urls:
        print(' threading %s -----> %s ' % (threading.current_thread().name, url))
        time.sleep(random.random())
    print('%s ended.' % threading.current_thread().name)

if __name__ == '__main__':
    # 创建两个线程实例
    t1 = threading.Thread(target=t_run, name='Thread_1', args=(['url1', 'url2'],))
    t2 = threading.Thread(target=t_run, name='Thread_2', args=(['url3', 'url4'],))
    # 启动线程
    t1.start()
    t2.start()
    # 等待线程结束
    t1.join()
    t2.join()
    print('%s ended.' % threading.current_thread().name)

第二种方式用threading.Thread继承创建线程类

# -*- coding: utf-8 -*-

import time
import random
import threading

class MyThread(threading.Thread):
    """
    定义线程类
    """

    def __init__(self, name, urls):
        """
        初始化，重写线程
        """
        threading.Thread.__init__(self, name=name)
        self.urls = urls

    def run(self):
        """
        执行函数
        """
        # 打印当前线程名
        print('Current %s is running...' % threading.current_thread().name)
        for url in self.urls:
            print('Thread %s ------> %s' % (threading.current_thread().name, url))
            time.sleep(random.random())
        print('%s ended.' % threading.current_thread().name)

if __name__ == '__main__':
    print('%s is running...' % threading.current_thread().name)
    t1 = MyThread(name='Thread_1', urls=['url1', 'url2'])
    t2 = MyThread(name='Thread_2', urls=['url3', 'url4'])
    t1.start()
    t2.start()
    t1.join()
    t2.join()
    print('%s ended.' % threading.current_thread().name)

from multiprocessing.dummy import Pool as ThreadPool
if __name__ == '__main__':
    pool = ThreadPool() #默认为5
    pool.map(main,[i*10 for i in range(10)])##多线程工作
    pool.close()
    pool.join()

from queue import Queue
from threading import Thread

queue_url = Queue(maxsize=10)  # 设置队列最大空间为10
result_queue = Queue()
for i in range(10):
    t = Thread(target=mian, args=(i,))
    t.start() 
print('main thread stop')