python简易爬虫

这篇文章主要讲解 python如何实现简易爬虫

爬虫流程

打开种子url —-> 获取种子url页面中所有的url —-> 判断是否被爬取过，未爬取过的url添加到url列表中 —-> 解析页面中需要的信息 —-> 写入数据库

上述流程中可以抽象出5个对象：

• bootstrap 启动器
• downloader 下载器
• parser 解析器
• url_manager url管理器
• outputer 输出器

启动器(main.py)

先看启动器是如何实现的：

#!/usr/bin/env python
# _*_ coding:utf-8 _*_
"""
Created on 2017/9/23
@author: tt
"""

import spider_outputer
import spider_parser

import spider_downloader
import spider_url_manager


class Main:
    def __init__(self):
        self.urls = spider_url_manager.UrlManager()
        self.downloader = spider_downloader.Downloader()
        self.outputer = spider_outputer.Outputer()
        self.parser = spider_parser.Parser()

    def craw(self, root_url):
        self.urls.add_new_url(root_url)
        count = 1
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print('craw %d : %s' % (count, new_url))
                html_content = self.downloader.download(new_url)
                new_urls, new_data = self.parser.parser(new_url, html_content)
                self.urls.add_new_urls(new_urls)
                self.outputer.collect_data(new_data)
                count += 1
            except Exception as e:
                print(e)


if __name__ == "__main__":
    url = 'https://www.zhihu.com/people/li-xiao-miao-70/activities'
    main = Main()
    main.craw(url)

下载器(spider_downloader.py)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Created on 2017/9/23
@author: tt
"""
import string
from urllib import request
from urllib.parse import quote

user_agent = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36'


class Downloader:
    def download(self, url):
        if url is None:
            return None
        _url = quote(url, safe=string.printable)
        req = request.Request(_url, headers={'User-Agent': user_agent})
        response = request.urlopen(req)
        if response.getcode() != 200:
            print("request bad")
            return None
        html = response.read()
        return html.decode('utf8')

解析器(spider_parser.py)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Created on 2017/9/23
@author: tt
"""
from urllib import parse

from bs4 import BeautifulSoup

import user_info


class Parser:
    def parser(self, page_url, html_content):
        if page_url is None or html_content is None:
            return
        soup = BeautifulSoup(html_content, "html.parser")
        new_urls = self._get_new_urls(page_url, soup)
        new_data = self._get_new_data(page_url, soup)
        return new_urls, new_data

    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        links = soup.find_all('a')
        for link in links:
            new_url = link.get('href')
            new_full_url = parse.urljoin(page_url, new_url)
            new_urls.add(new_full_url)
        return new_urls

    def _get_new_data(self, page_url, soup):
        ret_data = []
        author_infos = soup.find_all(class_='AuthorInfo')
        print(len(author_infos))
        for author_info in author_infos:
            user_id = author_info.find(class_='UserLink-link').get('href')
            user_id = user_id[user_id.find('e/') + 2:]
            photo = author_info.find(class_='AuthorInfo-avatar').get('srcset')
            pos = photo.find(' ')
            photo = photo[:pos]
            name = author_info.find('meta', attrs={"itemprop": "name"}).get('content')
            profession = author_info.find(class_='AuthorInfo-badgeText').get_text()

            user = user_info.UserInfo(user_id, name, photo, profession)
            ret_data.append(user)

        return ret_data

url管理器(spider_url_manager.py)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Created on 2017/9/23
@author: tt
"""


class UrlManager:
    def __init__(self):
        self.visited_url = set()
        self.visit_url = set()

    def add_new_url(self, url):
        if url is None:
            return
        if url not in self.visit_url and url not in self.visited_url:
            self.visit_url.add(url)

    def has_new_url(self):
        return len(self.visit_url) != 0

    def add_new_urls(self, urls):
        if urls is None or len(urls) == 0:
            return
        for url in urls:
            self.add_new_url(url)

    def get_new_url(self):
        new_url = self.visit_url.pop()
        self.visited_url.add(new_url)
        return new_url

输出器(spider_outputer.py)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Created on 2017/9/23
@author: tt
"""
import user_dao


class Outputer:
    def __init__(self):
        self.user_dao = user_dao.UserDao()

    def collect_data(self, data):
        if data is None:
            print('None')
            return
        else:
            for d in data:
                self.user_dao.add_user(d)

其他类

数据库帮助类(db_helper.py)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Created on 2017/9/23
@author: tt
"""
import pymysql


class DbHelper:
    def _get_connection(self):
        return pymysql.Connect(host='127.0.0.1', user='root', passwd='root', db='crawler', port=3306, charset='utf8')

    def execute_update(self, sql, params):
        connectin = self._get_connection()
        cursor = connectin.cursor()
        try:
            if params is None:
                s = sql
            else:
                s = (sql % params)
            result = cursor.execute(s)
            connectin.commit()
            print('rows:', result)
        except Exception as e:
            print(e)
            connectin.rollback()
        finally:
            cursor.close()
            connectin.close()

    def query(self, sql, params=None):
        connection = self._get_connection()
        cursor = connection.cursor()
        try:
            if params is None:
                s = sql
            else:
                s = (sql % params)
            cursor.execute(s)
            rows = cursor.fetchall()
            for row in rows:
                print(row)
        except Exception as e:
            print(e)
            connection.rollback()
        finally:
            cursor.close()
            connection.close()

用户数据访问类(user_dao.py)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Created on 2017/9/23
@author: tt
"""
import db_helper


class UserDao:
    def __init__(self):
        self.db = db_helper.DbHelper()

    def add_user(self, user):
        sql = '''INSERT IGNORE INTO zhihu_user(user_id, photo, name, profession) values('%s', '%s', '%s', '%s')'''
        params = (user.user_id, user.photo, user.name, user.profession)
        self.db.execute_update(sql=sql, params=params)

用户信息类(user_info.py)

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Created on 2017/9/23
@author: tt
"""


class UserInfo:
    def __init__(self, user_id, name, photo, profession):
        self.user_id = user_id
        self.name = name
        self.photo = photo
        self.profession = profession

    def __str__(self):
        return 'UserInfo(name=' + self.name + ', photo=' + self.photo + ", profession=" + self.profession + ')\n'

    def __repr__(self):
        return self.__str__()

在python中print在输出对象是调用的是对象的__str__函数

这个小的demo爬取的是知乎用户id，头像，名称，职业信息