/****
* 下载pdf文件
*/
public static void downloadNet(String urlStr, String fileName, String savePath) throws MalformedURLException {
// 下载网络文件
int bytesum = 0;
int byteread = 0;
// System.out.println(fileName); URL url = new URL(urlStr); try {
URLConnection conn = url.openConnection();
conn.setConnectTimeout(30000);
conn.setReadTimeout(30000);
conn.setRequestProperty("Host", "paper.cnstock.com");
conn.setRequestProperty("User-Agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:53.0) Gecko/20100101 Firefox/53.0");
conn.setRequestProperty("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8");
conn.setRequestProperty("Accept-Language", "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3");
conn.setRequestProperty("Accept-Encoding", "utf8, deflate");//注意编码,gzip可能会乱码
conn.setRequestProperty("Content-Encoding", "utf8");
conn.setRequestProperty("Connection", "keep-alive");
conn.setRequestProperty("Upgrade-Insecure-Requests", "1");
conn.setRequestProperty("Cookie", cookie);
conn.setRequestProperty("Cache-Control", "max-age=0");
conn.setRequestProperty("Content-Type", "application/pdf"); // savePage(page,savePath,fileName); InputStream inStream = conn.getInputStream();
FileOutputStream fs = new FileOutputStream(savePath + fileName); byte[] buffer = new byte[1204];
int length;
while ((byteread = inStream.read(buffer)) != -1) {
bytesum += byteread;
// System.out.println(bytesum);
fs.write(buffer, 0, byteread);
}
inStream.close();
fs.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
conn.setRequestProperty("Accept-Encoding", "utf8, deflate");//注意编码,gzip可能会乱码
总结:
采集文件出现异常,用记事本打开文件查看数据,与实际页面作对比,判断是否是乱码。乱码出现的很大可能就是文件的请求编码问题