沒有結(jié)果也沒有報錯啊
#?-*-?coding:?utf-8?-*-
from?baike_spider?import?url_manager,?html_downloader,?html_parser,?html_outputer
import?traceback
class?Spidermain(object):
????def?__init__(self):
????????self.urls?=?url_manager.UrlManger()
????????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_rul():
????????????try:
????????????????new_url?=?self.urls.get_new_url()
????????????????print?'craw?%d?:?%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)
????????????????if?count?==?1000:
????????????????????break
????????????????count?=?count?+?1
????????????except?Exception?as?e:
????????????????print?traceback.format_exc()
????????self.outputer.output_html()
if?__name__?==?"main":
????root_url?=?"http://baike.baidu.com/view/21087.htm"
????obj_spider?=?Spidermain()
????obj_spider.craw(root_url)
????
管理器
#?-*-?coding:?utf-8?-*-
class?UrlManger(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)
????????????#?not?in?waiting?list?and?not?in?old?list,?so?add?it?to?waitinglist
????def?add_new_urls(self,?urls):
????????if?urls?is?None?or?len(urls)?==?0:
????????????return
????????for?url?in?urls:
????????????self.add_new_url(url)
????????????#?iteration?
????def?has_new_rul(self):
????????return?len(self.new_urls)?!=?0
????def?get_new_url(self):
????????new_url?=?self.new_urls.pop()
????????self.old_urls.add(new_url)
????????#?pop?new_url?form?self.new_ruls?and?add?it?to?old?list
????????return?new_url
下載器
import?urllib2
class?HtmlDownloader(object):
????def?download(self,?url):
????????if?url?is?None:
????????????return?None
????????response?=?urllib2.urlopen(url)
????????if?response.getcode()?!=?200:
????????????return?None
????????return?response.read()
解析器
'''
@author:?erics
'''
from?bs4?import?BeautifulSoup
import?re
import?urlparse
class?HtmlParser(object):
????def?_get_new_urls(self,?page_rul,?soup):
????????new_urls?=?set()
????????#?/view/123.htm,?find?all?link?has?the?same?format
????????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_rul,?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
????def?parse(self,?page_rul,?html_cont):
????????if?page_rul?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_rul,?soup)
????????new_data?=?self._get_new_data(page_rul,?soup)
????????return?new_urls,?new_data
輸出器
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("<tr>%s</td>"?%?data['url'])
????????????fout.write("<tr>%s</td>"?%?data['title'].encode('utf-8'))
????????????fout.write("<tr>%s</td>"?%?data['summary'].encode('utf-8'))
????????????fout.write("</tr>")
????????fout.write("</table>")
????????fout.write("</body>")
????????fout.write("</html>")
????????fout.close()
class?HtmlParser(object):
????def?_get_new_urls(self,?page_rul,?soup):
????????new_urls?=?set()
????????#?/view/123.htm,?find?all?link?has?the?same?format
????????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_rul,?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
????def?parse(self,?page_rul,?html_cont):
????????if?page_rul?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_rul,?soup)
????????new_data?=?self._get_new_data(page_rul,?soup)
????????return?new_urls,?new_data求助呀，為什么沒有結(jié)果也沒有報錯啊0 0？
C:\Python27\python.exe C:/Users/erics/PycharmProjects/imooc/baike_spider/spider_main.py
Process finished with exit code 0
2016-11-13
你的spider_main里的
if __name__ == __main__
錯了
2016-11-13
115行的page_url你寫錯了改改看
2016-11-13
me too
2016-10-31
注意引號，?title_node?=?soup.find('dd',?class_="lemmaWgt-lemmaTitle-title").find('h1')改成
?title_node?=?soup.find('dd',?class_="lemmaWgt-lemmaTitle-title").find("h1")試試呢
2016-10-21
me too