perl：获取同花顺数据--业绩预告，送股派息

perldoc LWP::UserAgent

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

编写  get_yjyg_10jqka.pl  如下

#!/usr/bin/perl
# perl 获取同花顺数据--业绩预告
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/yjyg/');

if ($response->is_success) {
   print $DATA $response->decoded_content;  # or whatever
   close $DATA;
   $tree->parse_file("data.html");
} else {
   print " get data failed.";
   exit;
}
 
my $title=  $tree->findvalue('/html/body//span[@class="text-value"]');
print " title is $title\n";
$title ='yjyg-2024Q1'; 
my $ps = 1;
print " pages is $ps\n";

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

for (my $n=1; $n<=$ps; $n++){
   open(my $T, ">", "$title-$n.csv");
   my @arr1= $tree->find_by_tag_name("tr") ;
   #shift @arr1;
   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 chcp 65001

perl get_yjyg_10jqka.pl 

生成 yjyg-2024Q1-1.csv 

---

编写  get_sgpx_10jqka.pl 如下

#!/usr/bin/perl
# perl 获取同花顺数据--送股派息
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/sgpx/');

if ($response->is_success) {
   print $DATA $response->decoded_content;  # or whatever
   close $DATA;
   $tree->parse_file("data.html");
} else {
   print " get data failed.";
   exit;
}
 
my $title=  $tree->findvalue('/html/body//span[@class="text-value"]');
print " title is $title\n";
$title ='sgpx-2023Y'; 
my $pages = $tree->findvalue('/html/body//span[@class="page_info"]');
my @ps = split('/', $pages);
print " $title pages is $ps[1]\n";
$tree->delete();

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

my $n =6;
open(my $T, ">", "$title-$n.csv");
for (my $i=1; $i<=$n; $i++){
   my $tree= HTML::TreeBuilder::XPath->new;
   $tree->parse_file("data$i.html");
   my @arr1= $tree->find_by_tag_name("tr") ;
   shift @arr1;
   if ($i>1){ shift @arr1;}
   foreach my $row (@arr1) {
      my @arr2= $row->content_list;
      my @str;
      foreach my $a (@arr2){ push @str, $a->as_text;}
      my $line = join(',', @str);     
      print $T "$line\n"; 
   }
   $tree->delete();
}
close $T;
print "gen: $title-$n.csv\n";

运行 perl get_sgpx_10jqka.pl 

 title is 2023年年报
 sgpx-2023Y pages is 6

生成 sgpx-2023Y-6.csv