perl：获取同花顺数据--业绩快报，业绩公告

belldeep

已于 2024-03-23 23:23:01 修改

阅读量661

点赞数 4

CC 4.0 BY-SA版权

分类专栏： perl 文章标签： perl UserAgent 10jqka

于 2024-03-23 22:35:54 首次发布

本文链接：https://blog.csdn.net/belldeep/article/details/136976930

perl 专栏收录该内容

17 篇文章

订阅专栏

perldoc LWP::UserAgent

如果没有安装，则安装模块，运行 cpanm LWP::UserAgent 。

编写 get_yjkb_10jqka.pl 如下

#!/usr/bin/perl
# perl 获取同花顺数据--业绩快报
use LWP::UserAgent;
use Encode qw(decode encode);
use POSIX;
use Data::Dumper;
use HTML::TreeBuilder;
use HTML::TreeBuilder::XPath;

my $tree= HTML::TreeBuilder::XPath->new;
open(my $DATA,'>', "data.html") or die "open data file failed:$!"; 

my $ua = LWP::UserAgent->new;
$ua->timeout(10);
$ua->env_proxy;
$ua->agent("Mozilla/8.0");
my $response = $ua->get('http://data.10jqka.com.cn/financial/yjkb/');

if ($response->is_success) {
   print $DATA  $response->decoded_content;  # or whatever
#  print $response->decoded_content;  # or whatever
   $tree->parse_file( "data.html");
};

my $title=  $tree->findvalue('/html/body//span[@class="text-value"]');
print " title is $title\n";
$title ='yjkb-2023Y'; 
my $pages = $tree->findvalue('/html/body//span[@class="page_info"]');
my @ps = split('/', $pages);
print " $title pages is $ps[1]\n";

sub utf2gbk { encode('gbk', decode('utf8', $_[0]));} 
# 表头一行
my $headline ="序号,股票代码,股票简称,公告日期,营业收入(元),去年同期(元),同比增长(%),季度环比增长(%),净利润(元),去年同期(元),同比增长(%),季度环比增长(%),每股收益(元),每股净资产(元),净资产收益率(%),更多\n";

for (my $n=1; $n<=1; $n++){
   open(my $T, ">", "$title-$n.csv");
   print $T utf2gbk($headline);
   my @arr1= $tree->find_by_tag_name("tr") ;
   shift @arr1; shift @arr1; # 忽略表头2行
   foreach my $row (@arr1) {
      my @arr2= $row->content_list;
      my @str;
      foreach my $a (@arr2){ push @str, $a->as_text;}
      my $line = utf2gbk(join(',', @str));     
      print $T "$line\n"; 
   }
   close $T;
}

注意：源程序编码：UTF-8.

运行 cmd

chcp 65001

perl get_yjkb_10jqka.pl

title is 2023年年报
yjkb-2023Y pages is 23

生成 yjkb-2023Y-1.csv

编写 get_yjgg_10jqka.pl 如下

#!/usr/bin/perl
# perl 获取同花顺数据--业绩公告
use LWP::UserAgent;
use Encode qw(decode encode);
use POSIX;
use Data::Dumper;
use HTML::TreeBuilder;
use HTML::TreeBuilder::XPath;

my $tree= HTML::TreeBuilder::XPath->new;
open(my $DATA,'>', "data.html") or die "open data file failed:$!"; 

my $ua = LWP::UserAgent->new;
$ua->timeout(10);
$ua->env_proxy;
$ua->agent("Mozilla/8.0");
my $response = $ua->get('http://data.10jqka.com.cn/financial/yjgg/');

if ($response->is_success) {
   print $DATA  $response->decoded_content;  # or whatever
#  print $response->decoded_content;  # or whatever
   $tree->parse_file( "data.html");
};

my $title=  $tree->findvalue('/html/body//span[@class="text-value"]');
print " title is $title\n";
$title ='yjgg-2023Y'; 
my $pages = $tree->findvalue('/html/body//span[@class="page_info"]');
my @ps = split('/', $pages);
print " $title pages is $ps[1]\n";

sub utf2gbk { encode('gbk', decode('utf8', $_[0]));} 

# 表头一行
my $headline ="序号,股票代码,股票简称,公告日期,营业收入(元),去年同期(元),同比增长(%),季度环比增长(%),净利润(元),去年同期(元),同比增长(%),季度环比增长(%),每股收益(元),每股净资产(元),净资产收益率(%),更多\n";

for (my $n=1; $n<=1; $n++){
   open(my $T, ">", "$title-$n.csv");
   print $T utf2gbk($headline);
   my @arr1= $tree->find_by_tag_name("tr") ;
   shift @arr1; shift @arr1; # 忽略表头2行
   foreach my $row (@arr1) {
      my @arr2= $row->content_list;
      my @str;
      foreach my $a (@arr2){ push @str, $a->as_text;}
      my $line = utf2gbk(join(',', @str));     
      print $T "$line\n"; 
   }
   close $T;
}

运行 perl get_yjgg_10jqka.pl

title is 2023年年报
yjgg-2023Y pages is 7

生成 yjgg-2023Y-1.csv