-
444查看全部
-
333查看全部
-
222查看全部
-
URL管理器功能查看全部
-
运行流程查看全部
-
class HtmlOutputer(object): def __init__(self): self.datas=[]#列表 #收集数据 def collect_data(self,data): if data is None: return self.datas.append(data) #输出HTML内容 def output_html(self): fout=open('output.html','w')#输出到output.html中,w为写模式 fout.write("<html>") fout.write("<body>") fout.write("<table>") #ASCI 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>")查看全部
-
from bs4 import BeautifulSoup import re import urlparse class HtmlParser(object): def _get_new_urls(self, page_url, soup): new_urls = set() 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 = {} 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.parse', 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查看全部
-
HTML下载器查看全部
-
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查看全部
-
简单爬虫架构查看全部
-
urllib2 下载网页添加特殊情景查看全部
-
beautiful语法查看全部
-
.......查看全部
举报
0/150
提交
取消