Python的学习笔记(五)(简单的爬虫)

1.简单爬虫的时间流程图

2.URL管理器

3.网页下载器
使用python内置的urllib2进行下载,此外还有requests这个更加优秀的下载器

示例代码:

# coding:utf8
import urllib2
import cookielib

url = "http://www.baidu.com"

print '第一种方法'
response1 = urllib2.urlopen(url)
print response1.getcode()
print len(response1.read())

print '第二种方法'
request = urllib2.Request(url)
request.add_header("user-agent", "Mozilla/5.0")
response2 = urllib2.urlopen(request)
print response2.getcode()
print len(response2.read())

print '第三种方法'
cj = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj))
urllib2.install_opener(opener)
response3 = urllib2.urlopen(url)
print response3.getcode()
print cj #打印出cookie
print response3.read()

4.网页解析器
正则表达式
html.parser
Beautiful Soup
lxml

完整示例代码:
以爬取百度百科相关词条1000个为例
1.spider_main.py: 入口函数

# encoding=utf8
from baike_spider import url_manager, html_downloader, html_parser,\
    html_outputer


class SpiderMain(object):
    def __init__(self):
        self.urls = url_manager.UrlManager()
        self.downloader = html_downloader.HtmlDownloader()
        self.parser = html_parser.HtmlParser()
        self.outputer = html_outputer.HtmlOutPuter()

    def craw(self, root_url):
        count = 1
        self.urls.add_new_url(root_url)
        while self.urls.has_new_url(): #如果有未下载的url
            try:
                new_url = self.urls.get_new_url() #取一个未下载的url
                print 'craw %d : %s'%(count,new_url)
                html_cont = self.downloader.download(new_url) #由下载器下载对应的url
                new_urls,new_data = self.parser.parse(new_url,html_cont) #由解析器解析得到urls和data
                self.urls.add_new_urls(new_urls) #将新的urls加入url管理器
                self.outputer.collect_data(new_data) #将新的数据收集

                if count == 1000:
                    break
                count = count + 1
            except:
                print 'craw failed'
        self.outputer.output_html() #输出生成一个html文件




if __name__ == "__main__":
#     root_url = "http://baike.baidu.com/view/21087.htm"
    root_url = "http://baike.baidu.com/view/9936357.htm"
    obj_spider = SpiderMain()
    obj_spider.craw(root_url)

2.url_manager.py url管理器

# encoding=utf8

class UrlManager(object):


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


    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


    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 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)

3.html_downloader.py 网页下载器

import urllib2

class HtmlDownloader(object):

    def download(self, url):
        if url is None:
            return None

        response = urllib2.urlopen(url)
        if response.getcode() == 200:
            return response.read()
        return None

4.html_parser.py 网页解析器

# encoding=utf8
import re
import urlparse
from bs4 import BeautifulSoup

class HtmlParser(object):


    def _get_new_urls(self, page_url, soup):
        new_urls = set()
        # /view/23242.html
        links = soup.find_all('a', href=re.compile(r'/view/\d+\.htm'))
        for link in links :
            new_url = link['href']
            new_full_url = urlparse.urljoin(page_url, new_url) 
            new_urls.add(new_full_url)
        return new_urls

    def _get_new_data(self, page_url, soup):
        res_data = {}
        res_data['url'] = page_url
        # <dd class="lemmaWgt-lemmaTitle-title"><h1>Python</h1></dd>
        title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find("h1")
        res_data['title'] = title_node.get_text()

        summary_node = soup.find('div', class_="lemma-summary")
        res_data['summary'] = summary_node.get_text()

        return res_data


    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_urls = self._get_new_urls(page_url, soup)
        new_data = self._get_new_data(page_url, soup)
        return new_urls, new_data

5.html_outputer.py 网页输出器

# encoding=utf8


class HtmlOutPuter(object):

    def __init__(self):
        self.datas = []

    def collect_data(self, data):
        if data is None:
            return 
        self.datas.append(data)


    def output_html(self):
        fout = open('output.html', 'w')
        fout.write("<html>")
        fout.write("<body>")
        fout.write("<table>")
        for data in self.datas:
            fout.write("<tr>")
            fout.write("<td>%s</td>" % data['url'])
            fout.write("<td>%s</td>" % data['title'].encode('utf-8'))
            fout.write("<td>%s</td>" % data['summary'].encode('utf-8'))
            fout.write("</tr>")
        fout.write("</table>")
        fout.write("</body>")
        fout.write("</html>")

        fout.close()

附件下载地址:
http://download.csdn.net/detail/u014267209/9513115