您好,登錄后才能下訂單哦!
這篇文章主要為大家展示了“python爬蟲的示例分析”,內(nèi)容簡而易懂,條理清晰,希望能夠幫助大家解決疑惑,下面讓小編帶領(lǐng)大家一起研究并學(xué)習(xí)一下“python爬蟲的示例分析”這篇文章吧。
爬蟲簡單架構(gòu)
程序入口函數(shù)(爬蟲調(diào)度段)
#coding:utf8 import time, datetime from maya_Spider import url_manager, html_downloader, html_parser, html_outputer class Spider_Main(object): #初始化操作 def __init__(self): #設(shè)置url管理器 self.urls = url_manager.UrlManager() #設(shè)置HTML下載器 self.downloader = html_downloader.HtmlDownloader() #設(shè)置HTML解析器 self.parser = html_parser.HtmlParser() #設(shè)置HTML輸出器 self.outputer = html_outputer.HtmlOutputer() #爬蟲調(diào)度程序 def craw(self, root_url): count = 1 self.urls.add_new_url(root_url) while self.urls.has_new_url(): try: new_url = self.urls.get_new_url() print('craw %d : %s' % (count, new_url)) html_content = self.downloader.download(new_url) new_urls, new_data = self.parser.parse(new_url, html_content) self.urls.add_new_urls(new_urls) self.outputer.collect_data(new_data) if count == 10: break count = count + 1 except: print('craw failed') self.outputer.output_html() if __name__ == '__main__': #設(shè)置爬蟲入口 root_url = 'http://baike.baidu.com/view/21087.htm' #開始時間 print('開始計(jì)時..............') start_time = datetime.datetime.now() obj_spider = Spider_Main() obj_spider.craw(root_url) #結(jié)束時間 end_time = datetime.datetime.now() print('總用時:%ds'% (end_time - start_time).seconds)
URL管理器
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
網(wǎng)頁下載器
import urllib import urllib.request class HtmlDownloader(object): def download(self, url): if url is None: return None #偽裝成瀏覽器訪問,直接訪問的話csdn會拒絕 user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)' headers = {'User-Agent':user_agent} #構(gòu)造請求 req = urllib.request.Request(url,headers=headers) #訪問頁面 response = urllib.request.urlopen(req) #python3中urllib.read返回的是bytes對象,不是string,得把它轉(zhuǎn)換成string對象,用bytes.decode方法 return response.read().decode()
網(wǎng)頁解析器
import re import urllib from urllib.parse import urlparse from bs4 import BeautifulSoup class HtmlParser(object): def _get_new_urls(self, page_url, soup): new_urls = set() #/view/123.htm links = soup.find_all('a', href=re.compile(r'/item/.*?')) for link in links: new_url = link['href'] new_full_url = urllib.parse.urljoin(page_url, new_url) new_urls.add(new_full_url) return new_urls #獲取標(biāo)題、摘要 def _get_new_data(self, page_url, soup): #新建字典 res_data = {} #url res_data['url'] = page_url #<dd class="lemmaWgt-lemmaTitle-title"><h2>Python</h2>獲得標(biāo)題標(biāo)簽 title_node = soup.find('dd', class_="lemmaWgt-lemmaTitle-title").find('h2') print(str(title_node.get_text())) res_data['title'] = str(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_url, html_content): if page_url is None or html_content is None: return None soup = BeautifulSoup(html_content, '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
網(wǎng)頁輸出器
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('maya.html', 'w', encoding='utf-8') fout.write("<head><meta http-equiv='content-type' content='text/html;charset=utf-8'></head>") fout.write('<html>') fout.write('<body>') fout.write('<table border="1">') # <th width="5%">Url</th> fout.write('''<tr width="90%"> <th>Theme</th> <th width="80%">Content</th> </tr>''') for data in self.datas: fout.write('<tr>\n') # fout.write('\t<td>%s</td>' % data['url']) fout.write('\t<td align="center"><a href=\'%s\'>%s</td>' % (data['url'], data['title'])) fout.write('\t<td>%s</td>\n' % data['summary']) fout.write('</tr>\n') fout.write('</table>') fout.write('</body>') fout.write('</html>') fout.close()
運(yùn)行結(jié)果
以上是“python爬蟲的示例分析”這篇文章的所有內(nèi)容,感謝各位的閱讀!相信大家都有了一定的了解,希望分享的內(nèi)容對大家有所幫助,如果還想學(xué)習(xí)更多知識,歡迎關(guān)注億速云行業(yè)資訊頻道!
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點(diǎn)不代表本網(wǎng)站立場,如果涉及侵權(quán)請聯(lián)系站長郵箱:is@yisu.com進(jìn)行舉報,并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。