Python3爬取豆瓣网电影信息

 
# -*- coding:utf-8 -*-
"""
一个简单的Python爬虫, 用于抓取豆瓣电影Top前250的电影的名称
Language: Python3.6
"""
import re
import urllib.request
import urllib.error
import time

#import urllib2
import ssl

ssl._create_default_https_context = ssl._create_unverified_context
class DouBanSpider(object):
    """类的简要说明
    本类主要用于抓取豆瓣前100的电影名称

    Attributes:
        page: 用于表示当前所处的抓取页面
        cur_url: 用于表示当前争取抓取页面的url
        datas: 存储处理好的抓取到的电影名称
        _top_num: 用于记录当前的top号码
    """

    def __init__(self):
        self.page = 1
        self.cur_url = "http://movie.douban.com/top250?start={page}&filter=&type="
        self.datas = []
        self._top_num = 1
        print("豆瓣电影爬虫准备就绪, 准备爬取数据...")

    def get_page(self, cur_page):
        """
        根据当前页码爬取网页HTML
        Args:
            cur_page: 表示当前所抓取的网站页码
        Returns:
            返回抓取到整个页面的HTML(unicode编码)
        Raises:
            URLError:url引发的异常
        """
        url = self.cur_url
        time.sleep(3)

        try:
            #print(cur_page)
            page = (cur_page - 1) * 25
            #print(page)
            url = url.format(page=page)
            headers = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36'
            }
            request = urllib.request.Request(url, headers=headers)
            my_page = urllib.request.urlopen(request).read().decode('utf-8')

            print("请求第{}页,url地址是:{}".format(cur_page,url))

            #print(my_page)
        #urllib.error.URLError  #urllib.request.urlopen.URLError
        except urllib.error.URLError as e:
            if hasattr(e, "code"):
                print("The server couldn't fulfill the request.")
                print("Error code: %s" % e.code)
            elif hasattr(e, "reason"):
                print("We failed to reach a server. Please check your url and read the Reason")
                print("Reason: %s" % e.reason)
        return my_page


    def find_title(self, my_page):
        """
        通过返回的整个网页HTML, 正则匹配前100的电影名称
        Args:
            my_page: 传入页面的HTML文本用于正则匹配
        """
        temp_data = []
        #<span class="title">.*</span>
        #class="">[\s]+<span class="title">(.*?)</span>
        #<span.*?class="title">(.*?)</span>
        movie_items = re.findall(r'<span.*?class="title">(.*?)</span>', my_page, re.S)
        for index, item in enumerate(movie_items):
            if item.find("&nbsp") == -1:
                temp_data.append("Top" + str(self._top_num) + " " + item)
                self._top_num += 1
        self.datas.extend(temp_data)

    def start_spider(self):
        """
        爬虫入口, 并控制爬虫抓取页面的范围
        """
        while self.page <= 3:

            my_page = self.get_page(self.page)
            self.find_title(my_page)
            self.page += 1


def main():
    print(
    """
    ######################################
           一个简单的豆瓣电影前100爬虫
           Author: Agoly
           Version: Python3.6
           Date: 2019-09-06
    ######################################
    """)
    my_spider = DouBanSpider()
    my_spider.start_spider()
    for item in my_spider.datas:
        print(item)
    print("豆瓣爬虫爬取结束...")


if __name__ == '__main__':
    main()

 

 

 

 

 

 

posted @ 2019-09-06 20:01  Agoly  阅读(832)  评论(0编辑  收藏