本文的爬虫教程分为四部:
1.从哪爬 where
2.爬什么 what
3.怎么爬 how
4.爬了之后信息如何保存 save
一、从哪爬
三国演义
二、爬什么
三国演义全文
三、怎么爬
在Chrome页面打开F12,就可以发现文章内容在节点
<p id="con" class="bookyuanjiao">
只要找到这个节点,然后把内容写入到一个html文件即可。
content = soup.find("p", {"class": "bookyuanjiao", "id": "con"})
四、爬了之后如何保存
主要就是拿到内容,拼接到一个html文件,然后保存下来就可以了。
#!usr/bin/env # -*-coding:utf-8 -*- import urllib2 import os from bs4 import BeautifulSoup as BS import locale import sys from lxml import etree import re reload(sys) sys.setdefaultencoding('gbk') sub_folder = os.path.join(os.getcwd(), "sanguoyanyi") if not os.path.exists(sub_folder): os.mkdir(sub_folder) path = sub_folder # customize html as head of the articles input = open(r'0.html', 'r') head = input.read() domain = 'http://www.shicimingju.com/book/sanguoyanyi.html' t = domain.find(r'.html') new_domain = '/'.join(domain.split("/")[:-2]) first_chapter_url = domain[:t] + "/" + str(1) + '.html' print first_chapter_url # Get url if chapter lists req = urllib2.Request(url=domain) resp = urllib2.urlopen(req) html = resp.read() soup = BS(html, 'lxml') chapter_list = soup.find("p", {"class": "bookyuanjiao", "id": "mulu"}) sel = etree.HTML(str(chapter_list)) result = sel.xpath('//li/a/@href') for each_link in result: each_chapter_link = new_domain + "/" + each_link print each_chapter_link req = urllib2.Request(url=each_chapter_link) resp = urllib2.urlopen(req) html = resp.read() soup = BS(html, 'lxml') content = soup.find("p", {"class": "bookyuanjiao", "id": "con"}) title = soup.title.text title = title.split(u'_《三国演义》_诗词名句网')[0] html = str(content) html = head + html + "