如何得到每日排行榜

shijiang1130

http://tv.sohu.com/hotdrama/?d

arserangel

这是什么意思？抓取网页，然后分析其中的内容不就得到了么？

会当凌绝顶聪

继续！等着下文呢　！

shijiang1130

会当凌绝顶聪 发表于 2014-10-27 10:22
继续！等着下文呢　！

1. -module(sohu_tv).
   
2. -compile([export_all]).
   
3. 
   
4. -define(USER_AGENT_HEADER,{"User-Agent","Mozilla/5.0 (Windows NT 6.0) AppleWebKit/534.24 (KHTML, like Gecko) Chrome/11.0.696.68 Safari/534.24"}).
   
5. -define(LOG_FILE,?MODULE ++ ".log").
   
6. -define(LINKS_FILE,"links.log").
   
7. 
   
8. go()->
   
9.     inets:start(),
   
10.     case httpc:request(get,{"http://tv.sohu.com/hotdrama/?d",[?USER_AGENT_HEADER]},[{autoredirect,false}],[]) of
    
11.     {ok, {{_Version, StatusCode, _ReasonPhrase}, _, _Body}} when StatusCode==301; StatusCode==302 ->
    
12.         StatusCode;
    
13.     {ok, {{_Version, _StatusCode, _ReasonPhrase}, _Headers, Body}} ->
    
14.        parse_links(Body);
    
15.     {error,Reason} ->
    
16.         [Reason]
    
17.     end.
    
18. 
    
19. 
    
20. parse_links(Body) ->
    
21.     Regexp = "href\s*?=\s*?\"([^\"]+?)\"",
    
22.     case re:run(Body,Regexp,[{capture,all,list},global]) of
    
23.     {match,Matches} ->
    
24.         [file:write_file(?LINKS_FILE,Link ++ "\r\n",[append]) || [_Match,Link] <- Matches];
    
25.     nomatch ->
    
26.         []
    
27.     end.   
    
28. 
    
29. log_timestamp() ->
    
30.     {{Year,Mon,Day},{Hour,Min,Sec}} = erlang:localtime(),   
    
31.     io_lib:fwrite("~w/~2.2.0w/~2.2.0w ~2.2.0w:~2.2.0w:~2.2.0w",[Year,Mon,Day,Hour,Min,Sec]).
    
32. 
    
33.    
    
34.    
    

复制代码

shijiang1130

您给改改