首页 > 代码库 > 天涯抓取
天涯抓取
#_*_coding:utf-8-*-import urllib2import tracebackimport codecsfrom BeautifulSoup import BeautifulSoupdef openSoup(url,code): page = urllib2.urlopen(url) soup = BeautifulSoup(page,fromEncoding=code)#,fromEncoding="gb2312" #soup = BeautifulSoup(page,code) return soupdef getContentFromDiv(contents): s = "" for content in contents: try: s += content except: pass s = s.lstrip().rstrip() if len(s) < 50: return "" else: return " "+s+"\r\n"+"\r\n"def readHtml(soup,fp,authname): pageContent = "" item = soup.find(name=‘div‘, attrs={‘class‘:‘bbs-content clearfix‘}) if item != None: pageContent += getContentFromDiv(item.contents) items = soup.findAll(name=‘div‘, attrs={‘class‘:‘atl-item‘}) for item in items: userItem = item.find(name=‘a‘, attrs={‘class‘:‘js-vip-check‘}) if userItem == None or userItem.contents[0] != authname: continue contentItem = item.find(name=‘div‘, attrs={‘class‘:‘bbs-content‘}) pageContent += getContentFromDiv(contentItem.contents) fp.write(pageContent) def getNextPage(soup,pno): nextlink = soup.find(name="a",attrs={"class":"js-keyboard-next"}) if nextlink != None: return "http://bbs.tianya.cn"+nextlink["href"] else: return ‘OVER‘ def getAuthor(soup): div = soup.find(name=‘div‘, id="post_head") link = div.find(name="a",attrs={"class":"js-vip-check"}) return link["uname"]def makeFilename(url): return url[url.rindex("/"):][1:].replace("shtml","txt")def getHtml(url): filename = makeFilename(url) p = 1 fp = codecs.open(filename,‘w‘,‘utf-8‘) while True: soup = openSoup(url,‘utf-8‘) authname = getAuthor(soup) readHtml(soup,fp,authname) url = getNextPage(soup,p+1) if url == ‘OVER‘ : break print ‘PAGE ‘+str(p)+‘ OK‘ p = p + 1 print ‘It\‘s Over‘ fp.close()if __name__ == ‘__main__‘: getHtml(‘http://bbs.tianya.cn/post-worldlook-1219340-1.shtml‘)
声明:以上内容来自用户投稿及互联网公开渠道收集整理发布,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任,若内容有误或涉及侵权可进行投诉: 投诉/举报 工作人员会在5个工作日内联系你,一经查实,本站将立刻删除涉嫌侵权内容。