def getLocation(phoneNumber):
htmlGraber = HtmlGraber()
url = serviceUrl + "?m=" + phoneNumber
content = htmlGraber.doGrab(url)
content = content.replace("<br/><br/>", "||")
items = content.split("||")
# print items[1];
return items[1]
'''
Created on 2012-9-21
@author: sniperwang
'''
import re
from HtmlGraber import HtmlGraber
from BeautifulSoup import BeautifulSoup
from FileUtil import FileUtil;
import time;
import os;
import sys,getopt;
TOTALPAGES=1;
htmlGraber=HtmlGraber();
bbsHome="https://bbs.sjtu.edu.cn/";
savePathRoot="E:\\ppp\\";
def getHomePage(homeurl):
patt=re.compile(r'bbstcon,board,PPPerson,reid.*');
htmlContent=htmlGraber.doGrab(homeurl);
soup=BeautifulSoup(htmlContent);
urlPages=soup.findAll("a",href=re.compile(patt));
# print "\n".join([bbsHome+str(item.attrs[0][1]) for item in urlPages]);
return [bbsHome+str(item.attrs[0][1]) for item in urlPages];
def getPrePage(url):
patt=re.compile(r'bbstdoc,board,PPPerson,page.*');
htmlContent=htmlGraber.doGrab(url);
soup=BeautifulSoup(htmlContent);
'''
Created on 2012-11-7
@author: sniperwang
'''
import re
from BeautifulSoup import BeautifulSoup
from HtmlGraber import HtmlGraber
from FileUtil import FileUtil;
if __name__ == '__main__':
pass
#url="http://share.renren.com/share/249317678/14623723075?from=0101010302&ref=hotnewsfeed&sfet=104&fin=36&fid=20148636643&ff_id=249317678";
PicUrlHead="http://share.renren.com/share/249317678/14623723075/?photoId=";
htmlGraber=HtmlGraber();
maxCount=50;
firstIndex=249317678-50;
fileUtil=FileUtil();
homeSavePath="E:\\temp\\"
def grabImageUrl(picUrl):
patt=re.compile(r'http://fmn.rrimg.com/.*');
htmlContent=htmlGraber.doGrab(picUrl);
# print htmlContent;
soup=BeautifulSoup(htmlContent);
imgurls=soup.findAll('img',id="photo");#re.compile(patt));
#print str(imgurl[0].src);
# print "\n".join([str(item) for item in imgurls]);
if(len(imgurls)>0):
return imgurls[0]["src"];
