Python 网络爬虫（新闻采集脚本）

=====================爬虫原理=====================

通过Python访问新闻首页，获取首页所有新闻链接，并存放至URL集合中。

逐一取出集合中的URL，并访问链接获取源码，解析出新的URL链接添加到集合中。

为防止重复访问，设置一个历史访问，用于对新添加的URL进行过滤。

解析DOM树，获取文章相关信息，并将信息存储到Article对象中。

将Article对象中的数据通过pymysql保存到数据库中。

每完成一次数据的存储，计数器增加并打印文章标题，否则打印错误信息。

如果集合中的URL全部读取完或数据数量达到设定值，程序结束。

=====================存储结构=====================

CREATE TABLE `news` (
  `id` int(6) unsigned NOT NULL AUTO_INCREMENT,
  `url` varchar(255) NOT NULL,
  `title` varchar(45) NOT NULL,
  `author` varchar(12) NOT NULL,
  `date` varchar(12) NOT NULL,
  `about` varchar(255) NOT NULL,
  `content` text NOT NULL,
  PRIMARY KEY (`id`),
  UNIQUE KEY `url_UNIQUE` (`url`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

=====================脚本代码=====================

‘‘‘
百度百家新闻收集
‘‘‘

import re  # 网络连接模块
import bs4  # DOM解析模块
import pymysql  # 数据库连接模块
import urllib.request  # 网络访问模块

# 配置参数
maxcount = 1000  # 数据数量
home = ‘http://baijia.baidu.com/‘  # 起始位置
# 数据库连接参数
db_config = {
    ‘host‘: ‘localhost‘,
    ‘port‘: ‘3310‘,
    ‘username‘: ‘woider‘,
    ‘password‘: ‘3243‘,
    ‘database‘: ‘python‘,
    ‘charset‘: ‘utf8‘
}

url_set = set()  # url集合
url_old = set()  # 过期url

# 获取首页链接
html = urllib.request.urlopen(home).read().decode(‘utf8‘)
soup = bs4.BeautifulSoup(html, ‘html.parser‘)
pattern = ‘http://\w+\.baijia\.baidu\.com/article/\w+‘
links = soup.find_all(‘a‘, href=re.compile(pattern))
for link in links:
    url_set.add(link[‘href‘])

# 文章类定义
class Article(object):
    def __init__(self):
        self.url = None
        self.title = None
        self.author = None
        self.date = None
        self.about = None
        self.content = None

# 连接数据库
connect = pymysql.Connect(
    host=db_config[‘host‘],
    port=int(db_config[‘port‘]),
    user=db_config[‘username‘],
    passwd=db_config[‘password‘],
    db=db_config[‘database‘],
    charset=db_config[‘charset‘]
)
cursor = connect.cursor()

# 处理URL信息
count = 0
while len(url_set) != 0:
    try:
        # 获取链接
        url = url_set.pop()
        url_old.add(url)

        # 获取代码
        html = urllib.request.urlopen(url).read().decode(‘utf8‘)
        # DOM解析
        soup = bs4.BeautifulSoup(html, ‘html.parser‘)
        pattern = ‘http://\w+\.baijia\.baidu\.com/article/\w+‘  # 链接匹配规则
        links = soup.find_all(‘a‘, href=re.compile(pattern))

        # 获取URL
        for link in links:
            if link[‘href‘] not in url_old:
                url_set.add(link[‘href‘])

        # 数据防重
        sql = "SELECT id FROM news WHERE url = ‘%s‘ "
        data = (url,)
        cursor.execute(sql % data)
        if cursor.rowcount != 0:
            raise Exception(‘Data Repeat Exception: ‘ + url)

        # 获取信息
        article = Article()
        article.url = url  # URL信息
        page = soup.find(‘div‘, {‘id‘: ‘page‘})
        article.title = page.find(‘h1‘).get_text()  # 标题信息
        info = page.find(‘div‘, {‘class‘: ‘article-info‘})
        article.author = info.find(‘a‘, {‘class‘: ‘name‘}).get_text()  # 作者信息
        article.date = info.find(‘span‘, {‘class‘: ‘time‘}).get_text()  # 日期信息
        article.about = page.find(‘blockquote‘).get_text()
        pnode = page.find(‘div‘, {‘class‘: ‘article-detail‘}).find_all(‘p‘)
        article.content = ‘‘
        for node in pnode:  # 获取文章段落
            article.content += node.get_text() + ‘\n‘  # 追加段落信息

        # 存储数据
        sql = "INSERT INTO news( url, title, author, date, about, content ) "
        sql = sql + " VALUES (‘%s‘, ‘%s‘, ‘%s‘, ‘%s‘, ‘%s‘, ‘%s‘) "
        data = (article.url, article.title, article.author, article.date, article.about, article.content)
        cursor.execute(sql % data)
        connect.commit()

    except Exception as e:
        print(e)
        continue
    else:
        print(article.title)
        count += 1
    finally:
        # 判断数据是否收集完成
        if count == maxcount:
            break

# 关闭数据库连接
cursor.close()
connect.close()

=====================运行结果=====================

设置参数 maxcount = 10 , home = ‘http://baijia.baidu.com/‘

查询数据 SELECT title, author FROM python.news;