Python 爬虫爬取指定博客的所有文章

def updatePostsDB(request):
  #deleteAll()
  SiteInfos=[]
  SiteInfo={}
  SiteInfo['PostSite']="L2ZStory"
  SiteInfo['feedurl']="feed://l2zstory.wordpress.com/feed/"
  SiteInfo['blog_type']="wordpress"
  SiteInfos.append(SiteInfo)
  SiteInfo={}
  SiteInfo['PostSite']="YukiLife"
  SiteInfo['feedurl']="feed://blog.sina.com.cn/rss/1583902832.xml"
  SiteInfo['blog_type']="sina"
  SiteInfos.append(SiteInfo)
  SiteInfo={}
  SiteInfo['PostSite']="ZLife"
  SiteInfo['feedurl']="feed://ireallife.wordpress.com/feed/"
  SiteInfo['blog_type']="wordpress"
  SiteInfos.append(SiteInfo)
  SiteInfo={}
  SiteInfo['PostSite']="ZLife_Sina"
  SiteInfo['feedurl']="feed://blog.sina.com.cn/rss/1650910587.xml"
  SiteInfo['blog_type']="sina"
  SiteInfos.append(SiteInfo)
  
  try:
    for site in SiteInfos:
      feedurl=site['feedurl']
      blog_type=site['blog_type']
      PostSite=site['PostSite']
      PostInfos=getPostInfosFromWeb(feedurl,blog_type)
      recordToDB(PostSite,PostInfos)
    Msg="Cron Job Done..." 
  except Exception,e:
    Msg=str(e)  
  return HttpResponse(Msg)

import urllib
#from BeautifulSoup import BeautifulSoup
from pyquery import PyQuery as pq
def getArticleList(url):
  lstArticles=[]
  url_prefix=url[:-6]
  Cnt=1
  
  response=urllib.urlopen(url)
  html=response.read()
  d=pq(html)
  try:
    pageCnt=d("ul.SG_pages").find('span')
    pageCnt=int(d(pageCnt).text()[1:-1])
  except:
    pageCnt=1
  for i in range(1,pageCnt+1):
    url=url_prefix+str(i)+".html"
    #print url
    response=urllib.urlopen(url)
    html=response.read()
    d=pq(html)
    title_spans=d(".atc_title").find('a')
    date_spans=d('.atc_tm')
    
    for j in range(0,len(title_spans)):
      titleObj=title_spans[j]
      dateObj=date_spans[j]
      article={}
      article['link']= d(titleObj).attr('href')
      article['title']= d(titleObj).text()
      article['date']=d(dateObj).text()
      article['desc']=getPageContent(article['link'])
      lstArticles.append(article)
  return lstArticles
  
def getPageContent(url):
  #get Page Content
  response=urllib.urlopen(url)
  html=response.read()
  d=pq(html)
  pageContent=d("div.articalContent").text()
  #print pageContent
  return pageContent
def main():
  url='http://blog.sina.com.cn/s/articlelist_1191258123_0_1.html'#Han Han
  url="http://blog.sina.com.cn/s/articlelist_1225833283_0_1.html"#Gu Du Chuan Ling
  url="http://blog.sina.com.cn/s/articlelist_1650910587_0_1.html"#Feng
  url="http://blog.sina.com.cn/s/articlelist_1583902832_0_1.html"#Yuki
  lstArticles=getArticleList(url)
  for article in lstArticles:
    f=open("blogs/"+article['date']+"_"+article['title']+".txt",'w')
    f.write(article['desc'].encode('utf-8')) ＃特别注意对中文的处理
    f.close()
    #print article['desc']
    
if __name__=='__main__':
  main()