学习两周python之后,就学着写了个爬虫,实现对百度百科关键字python搜索100个相关链接页面的标题和摘要。
项目结构如下:
源代码如下:
html_downloader.py
# coding:utf-8
import urllib2
class HtmlDownloader():
def download(self, url):
if url is None:
return None
response = urllib2.urlopen(url)
if response.getcode() != 200:
return None
return response.read()
html_outper.py
# coding:utf-8
class HtmlOutputer(object):
def __init__(self):
self.datas = []
def collect_data(self, new_data):
if new_data is None:
return
self.datas.append(new_data)
def output_html(self):
try:
file = open("spider_output.html", "w")
file.write("<html><head><meta charset='UTF-8'></head><body><table>")
for data in self.datas:
file.write("<tr>")
file.write("<td>%s</td>" % data["url"])
file.write("<td>%s</td>" % data["title"].encode("utf-8"))
file.write("<td>%s</td>" % data["summary"].encode("utf-8"))
file.write("</tr>")
file.write("</table></body></html>")
except:
print "output_html error!"
finally:
file.close()
html_parser.py
# coding:utf-8
import re
import urlparse
from bs4 import BeautifulSoup
class HtmlParser():
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
def get_new_urls(self, page_url, soup):
new_urls = set()
links = soup.find_all("a", href=re.compile(r"/item/"))
for l in links:
new_url = l["href"]
new_full_link = urlparse.urljoin(page_url, new_url)
new_urls.add(new_full_link)
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()
'''
<div class="lemma-summary" label-module="lemmaSummary"></div>
'''
summary_node = soup.find("div", class_="lemma-summary")
res_data["summary"] = summary_node.get_text()
return res_data
url_manager.py
# coding:utf-8
class UrlManager():
'''
维护两个url集合,访问过的urls、待访问的urls
'''
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.old_urls and url not in self.new_urls:
self.new_urls.add(url)
def add_new_urls(self, new_urls):
if new_urls is None or len(new_urls) == 0:
return
for url in new_urls:
self.new_urls.add(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
spider_main.py
# coding:utf-8
import html_downloader
import html_outputer
import html_parser
import url_manager
class SpiderMan(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():
new_url = self.urls.get_new_url()
print "current url is %d , url = %s" % (count, 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)
count += 1
if (count == 100):
break
self.outputer.output_html()
if __name__ == "__main__":
root_url = "https://baike.baidu.com/item/Python/407313?fr=aladdin"
obj_spider = SpiderMan()
obj_spider.craw(root_url)
运行结果: