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]
homeurl="https://bbs.sjtu.edu.cn/bbstdoc,board,PPPerson.html";
pages=getHomePage(homeurl);
prePage=getPrePage(homeurl);
#grabImageUrls(pages[2]);
dateNow=getCurrentDate();
makeDirWhenNeeded(savePathRoot,dateNow);
for i in range(TOTALPAGES):
fileUtil=FileUtil();
for pageUrl in pages:
images=grabImageUrls(pageUrl);
# print "\n".join([str(item[0]) for item in images]);
for image in images:
fileName=image[0];
filePath=savePathRoot+getCurrentDate()+"\\"+fileName;
content=htmlGraber.doGrab(image[1]);
fileUtil.binaryWrite(filePath, content);
print fileName+" saved!";
pages=getHomePage(prePage);
prePage=getPrePage(prePage);
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"];
else:
return ""
fileUtil.makeDirWhenNeeded("E:\\temp\\", "renren");
for index in range(maxCount):
picId=firstIndex-index;
picUrl = PicUrlHead + str(picId);
print picUrl+"\n";
imgurl = grabImageUrl(picUrl);
if(imgurl != ""):
imgContent=htmlGraber.doGrab(imgurl);
fileUtil.binaryWrite("E:\\temp\\renren\\"+str(index)+".jpg", imgContent);
