下載器
官方庫urllib2和第三方庫request
解析器
Beautiful Soup（第三方庫），用於從HTML或XML中提取數據，官網http://www.crummy.com/software/BeautifulSoup/
安裝並測試beautifulsoup4
安裝：pip install beautifulsoup4
測試：
import bs4
print bs4
實例（確定目標、分析目標（url格式、數據格式、網頁編碼）、編寫代碼、執行爬蟲）：
# coding:utf-8
import re
from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup = BeautifulSoup(html_doc, 'html.parser', from_encoding='utf-8')
print '獲取所有的鏈接'
links = soup.find_all('a')
for link in links:
print link.name, link['href'], link.get_text()
print '獲取lacie的鏈接'
link_node = soup.find('a', href='http://example.com/lacie')
print link_node.name, link_node['href'], link_node.get_text()
print '獲取正則匹配的鏈接'
link_node = soup.find('a', href=re.compile(r"ill"))
print link_node.name, link_node['href'], link_node.get_text()
print '獲取p段落文字'
p_node = soup.find('p', class_="title")
print p_node.name, p_node.get_text()
結果：
獲取所有的鏈接
a http://example.com/elsie Elsie
a http://example.com/lacie Lacie
a http://example.com/tillie Tillie
獲取lacie的鏈接
a http://example.com/lacie Lacie
獲取正則匹配的鏈接
a http://example.com/tillie Tillie
獲取p段落文字
p The Dormouse’s story
實戰演練：
【慕課網-Python開發簡單爬蟲-第7章 實戰演練：爬取百度百科1000個頁面的數據】
代碼整理如下：
url_manager.py：
# coding:utf-8
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
html_downloader.py:
# coding:utf-8
import urllib2
class HtmlDownloader(object):
def download(self, url):
if url is None:
return None
response = urllib2.urlopen(url)
if response.getcode() != 200:
return None
return response.read()
html_parser.py:
# coding:utf-8
import re
import urlparse
from bs4 import BeautifulSoup
class HtmlParser(object):
def parse(self, page_url, html_cont):
if page_url is None or html_cont is None:
return
# 解析：獲取更多url和數據
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
def _get_new_urls(self, page_url, soup):
new_urls = set()
# /view/123.htm
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 = {}
# url
res_data['url'] = page_url
# <dd class="lemmaWgt-lemmaTitle-title">
# <h1>Python</h1>
title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find("h1")
res_data['title'] = title_node.get_text()
# <div class="lemma-summary" label-module="lemmaSummary">
summary_node = soup.find('div', class_="lemma-summary")
res_data['summary'] = summary_node.get_text()
return res_data
html_outputer.py:
# coding:utf-8
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>")
# ascii
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>")
spider_main.py:
# coding:utf-8
# 主文件：爬取百科Python及相關詞條，生成到output.html中
from baike_spider import url_manager, html_downloader, html_parser, html_outputer
class SpiderMain(object):
def __init__(self):
# url
self.urls = url_manager.UrlManager()
# 下載器
self.downloader = html_downloader.HtmlDownloader()
# 解析器
self.parser = html_parser.HtmlParser()
# 輸出器
self.outputer = html_outputer.HtmlOutputer()
# 調用程序
def craw(self, url):
# 記錄爬取的第幾個url
count = 1
self.urls.add_new_url(url)
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url()
print 'craw %d : %s' % (count, new_url)
# 讀取頁面內容
html_cont = self.downloader.download(new_url)
new_urls, new_data = self.parser.parse(new_url, html_cont)
# 解析後的url
self.urls.add_new_urls(new_urls)
# 解析後的數據
self.outputer.collect_data(new_data)
if count == 1000:
break
count = count + 1
except:
print 'craw failed'
self.outputer.output_html()
if __name__ == "__main__":
root_url = "http://baike.baidu.com/view/21087.htm"
obj_spider = SpiderMain()
obj_spider.craw(root_url)