niujiabenben

# coding: utf-8

"""
获取某个顶会的文章的引用数, 并输出其前10%的文章列表.
由于google scholor有防爬机制, 这里假定所有的html的源文件都手动下载到本地.
"""

import re
import os
from bs4 import BeautifulSoup

niujiabenben

#include "httpclient.h"

static inline size_t WriteCallback(void* contents, size_t size, size_t nmemb,
                                   void* userp) {
  ((std::string*) userp)->append((char*) contents, size * nmemb);
  return size * nmemb;
}

//////////////////////////// class HttpClient //////////////////////////////////

niujiabenben

extern "C" {
#include <jerror.h>
#include <jpeglib.h>
#include <setjmp.h>
}

struct JpegErrorManager {
  struct jpeg_error_mgr pub;
  jmp_buf setjmp_buffer;
};

niujiabenben

#include <lmdb.h>

#include "common.h"
#include "util.h"
#include "timer.h"

int main(int argc, char *argv[]) {
  google::InitGoogleLogging(argv[0]);
  google::LogToStderr();