python爬虫第二步---第一个完整的爬虫程序

流程图再补：
爬取内容：
1.1000个python百度百科词条的标题和简介信息
模块拆解：
1.程序启动器，爬虫调度器
2.url管理器
3.网页下载器
4.网页分析器
5.输出到html文件中
代码：
1.程序启动器，爬虫调度器 （创建对象，控制流程，循环）
#coding:utf-8
import url_manager
import html_downloader
import html_parser
import html_output
class SpiderMain():
def init(self):
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.HtmlDownloader()
self.parser = html_parser.HtmlParser()
self.outputer = html_output.HtmlOutput()
def craw(self, url):
count = 1
self.urls.add_new_url(root_url)
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url()
html_cont = self.downloader.download(new_url)
new_urls,new_data = self.parser.parse(new_url, html_cont)
self.urls.add_new_urls(new_urls)
self.outputer.collect_data(new_data)
if count == 1000:
break
count = count + 1
print (count)
except:
print (“craw failed!”)
self.outputer.output()
if name == ‘main’:
root_url = “http://baike.baidu.com/item/Python/407313?fr=aladdin”
obj_spider = SpiderMain()
obj_spider.craw(root_url)

2.url管理器（使用set去重，已爬取的放入old_url，未爬取的放入new_url）
#coding:utf-8
class UrlManager():
def init(self):
self.new_urls = set()
self.old_urls = set()
def get_new_url(self):
new_url = self.new_urls.pop()
self.old_urls.add(new_url)
return new_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)
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

3.网页下载器（获取网页信息）
#coding:utf-8
import urllib.request
class HtmlDownloader():
def download(self, url):
if url is None:
return
resp = urllib.request.urlopen(url)
if resp.getcode() !=200:
return None
return resp.read()

4.网页分析器（获取当前网页的url和data信息）
#coding:utf-8
import urllib.request
from urllib.parse import urljoin
from bs4 import BeautifulSoup
import re
import url_manager
class HtmlParser():
def get_new_urls(self,page_url,soup):
new_urls = set()
links = soup.find_all(‘a’, href = re.compile(r"/item/"))
for link in links:
new_url = link[‘href’]
new_full_url = 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
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.输出到html文件中
#coding:utf-8
class HtmlOutput():
def init(self):
self.datas = []
def collect_data(self,data):
if data is None:
return
self.datas.append(data)
def output(self):
fout = open(‘output.html’,‘w’***,encoding=‘utf-8’***)
fout.write("")
fout.write("")
fout.write("

")
for data in self.datas:
fout.write("")
fout.write(""% data[‘url’])
******title = data[‘title’].encode(‘utf-8’)
fout.write("" % str(title,‘utf-8’))
summary = data[‘summary’].encode(‘utf-8’)
fout.write("" % str(summary,‘utf-8’))******#这四行代码，执行出来显示的内容是b’\xe4…之类的，是16进制的byte编码，怎么都转换不成汉字。解决办法：在fout = open(‘output.html’,‘w’***,encoding=‘utf-8’***)加了编码参数。唉，心累，编码解码的原理还没理解到，待学习’
fout.write("")
fout.write("

%s

%s

%s

")
fout.write("")
fout.write("")