Instagramの猫画像クローラ crawl_instagram.cpp

crawl_instagram.cpp

#include <fstream>
#include <iostream>
#include <mutex>
#include <string>
#include <thread>

#include <restclient-cpp/restclient.h>

#include <json11.hpp>

static std::string client_id = "クライアントID";
static std::string endpoint = "https://api.instagram.com/v1/tags/sheep/media/recent?client_id=" + client_id;

std::mutex mux;
static inline void synched_cout(const std::string& message)
{
  std::lock_guard<std::mutex> lock{mux};
  std::cout << message << std::endl << std::flush;
}

void crawl_func(const std::string& url, const std::string& id)
{
  synched_cout("Download start: " + url);

  // download file and save
  auto raw_data = RestClient::get(url);
  std::ofstream out(id + ".jpg");
  out << raw_data.body;
  out.close();

  synched_cout("Download done: " + url);
}

int main()
{
  auto res = RestClient::get(endpoint);

  std::string err;
  auto json = json11::Json::parse(res.body, err);
  if(!err.empty())
  {
    std::cout << err << std::endl;
    return 1;
  }

  std::vector<std::thread> threads;

  auto data = json["data"].array_items();
  for(auto& item : data)
  {
    auto id = item["id"].string_value();
    auto url = item["images"]["standard_resolution"]["url"].string_value();

    threads.emplace_back(crawl_func, url, id);
  }

  for(auto& th : threads)
  {
    th.join();
  }

  return 0;
}