Python爬虫爬取博客园并保存       

爬取博客园指定用户的文章修饰后全部保存到本地

首先定义爬取的模块文件：

1. crawlers_main.py 执行入口
2. url_manager.py url管理器
3. download_manager.py 下载模块
4. parser_manager.py html解析器（解析html需要利用的内容)
5. output_manager.py 输出html网页全部内容文件（包括css,png,js等）

 

crawlers_main.py 执行入口

# coding:utf8
from com.crawlers import download_manager
from com.crawlers import output_manager
from com.crawlers import parser_manager
from com.crawlers import url_manager


class SpiderMain(object):
    def __init__(self):
        self.urls = url_manager.UrlManager()
        self.downloader = download_manager.DownloadManager()
        self.parser = parser_manager.ParserManager()
        self.output = output_manager.OutputManager()

    def craw(self, root_url):
        html_root = self.downloader.download(root_url)
        new_urls = self.parser.parseUrls(root_url,html_root)
        self.urls.add_new_urls(new_urls)
        count = 1
        while self.urls.has_new_url():
            try:
                new_url = self.urls.get_new_url()
                print('craw %d : %s' % (count, new_url))
                html_cont = self.downloader.download(new_url)
                new_data = self.parser.parse(new_url, html_cont)
                self.output.collect_data(new_data)
                if count == 1000:
                    break
                count += 1
            except:
                print('craw failed')

        self.output.output_html()


if __name__ == "__main__":
    root_url = "http://www.cnblogs.com/zhuyuliang/"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

url_manager.py url管理器

# coding:utf8
class UrlManager(object):

    def __init__(self):
        self.new_urls = set()
        self.old_urls = set()

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

    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 has_new_url(self):
        return len(self.new_urls) != 0

    def get_new_url(self):
        new_url = self.new_urls.pop()
        self.old_urls.add(new_url)
        return new_url

download_manager.py 下载模块

# coding:utf8
import urllib2


class DownloadManager(object):

    def download(self, url):
        if url is None:
            return None
        response = urllib2.urlopen(url)
        if response.code != 200:
            return None
        return response.read()

parser_manager.py html解析器（解析html需要利用的内容)

# coding:utf8
import re
from HTMLParser import HTMLParser

from bs4 import BeautifulSoup
import urlparse

import sys
reload(sys)
sys.setdefaultencoding('utf-8')

class ParserManager(HTMLParser):

    def __init__(self):
        HTMLParser.__init__(self)
        self.links = []

    def handle_starttag(self, tag, attrs):
        # print "Encountered the beginning of a %s tag" % tag
        if tag == 'img' or tag == "script":
            for (variable, value) in attrs:
                if variable == "src" or variable == "href":
                    self.links.append(value)
        if tag == "link":
            dic = dict(attrs)
            if dic['rel'] == "stylesheet":
                self.links.append(dic['href'])

    def parse(self, page_url, html_cont):
            if page_url is None or html_cont is None:
                return
            soup = BeautifulSoup(html_cont,'html.parser',from_encoding='utf-8')
            new_data = sel