查看“Astropy.io.fits”的源代码



 >>> hdulist = fits.open('input.fits')
 >>> hdulist.info()

==header==
 >>> hdr=hdulist[0].header
 >> list(hdr.keys())
 >>> hdr['targname']
 >>> header[:2] #只看前面两个
 >>> hdr.set('observer', 'Edwin Hubble') #添加header


* FITS标准使用的特定结构关键字集随HDU类型的不同而不同,还有许多其他保留的关键字，例如用于数据缩放的关键字，或用于表的列属性的关键字，如FITS标准中所述。其中大多数都可以通过Column或HDU对象的属性访问，例如用HDU .name设置EXTVER的 EXTNAME或HDU.ver。结构关键字将作为通用操作的结果进行检查和/或更新。例如,关键字NAXIS*从数据形状(.data.shape)中设置，BITPIX从数据类型(.data.dtype)中设置,调用HDU的验证方法(PrimaryHDU.verify()),一些关键字可以自动修复。

===comment/hitory===
 >>> hdr['history'] = 'I updated this file 2/26/09'
 >>> hdr['comment'] = 'Edwin Hubble really knew his stuff'
 >>> hdr['comment'] = 'I like using HST observations'
 >>> hdr['history']
 I updated this file 2/26/09
 >>> hdr['comment']
 Edwin Hubble really knew his stuff
 I like using HST observations
 >>> hdr['comment'][1] = 'I like using JWST observations'
 >>> hdr['comment']
 Edwin Hubble really knew his stuff
 I like using JWST observations

==fits table 的读与写==
*读
 hdu = fits.open('SFH_LMC3_out.fits')
 hdu.info() #看看哪些hdu
 data=hdu[1].data
 cols=hdu[1].columns
 data.columns #看看有那些列
 data.field(0) #读取第一列，也可以拿到列的名字，然后data['tag']读取
 data[0] #第一行
* 修改columns中某个keyword的值
 columns = fits.ColDefs(hdul[1].columns)
 clumns1.change_attrib(col_name='DATA',attrib='format',new_value='8388608B')
*写 
 from astropy.table import Table
 t=Table([Bage,fzbin,Age_weight2],names=('Age','z','weights'))
 t.write('SFH_LMC3_out.fits',format='fits')
*更新
:可以使用**HDUList.flush()方法将自open()**以来所做的所有更改写回原始文件。**close()**方法将对以更新模式打开的FITS文件执行相同的操作:
 with fits.open('original.fits', mode='update') as hdul:
    # Change something in hdul.
    hdul.flush()

==fits文件打开过多错误==
* [https://docs.astropy.org/en/stable/io/fits/appendix/faq.html#i-am-opening-many-fits-files-in-a-loop-and-getting-oserror-too-many-open-files]
* fits.close() 
* 可能还根系统设置有关  
 ulimit -a
 ulimit -n 100000
 vim /etc/security/limits.conf
* 把python的软限制编程硬限制,参见 [https://bbs.huaweicloud.com/blogs/108323],下面方法貌似也不管用
 import resource
 soft, hard = resource.getrlimit(resource.RLIMIT_NOFILE)
 resource.setrlimit(resource.RLIMIT_NOFILE, (hard, hard))
*lsof -p 进程id > openfiles.log命令，获得当前占用句柄的全部详情进行分析
* 实测这两个效果不好（python 3.8）
:*del hdu.data
:*hdu = fits.open(fits_name,memmap=False) #打开fits文件数目比较多的情况下

==fits image读写==
 n = np.arange(100.0) 
 hdu = fits.PrimaryHDU(n)
 hdu.writeto('new2.fits')
 hdu.writeto('new2.fits')
*如果超过一个hdu
 >>> hdul = fits.HDUList([hdu])
 >>> hdul.writeto('new1.fits')