1

我正在编写一个脚本来从我的 Flickr 帐户中提取其中所有照片的选定元数​​据。当脚本在照片集中移动时，我得到一个（看似）随机的ElementTree.ParseError：

File "flickr-get.py", line 95, in <module>
    get_photoset_metadata(key)
  File "flickr-get.py", line 51, in get_photoset_metadata
    photo = flickr.photos_getInfo(photo_id=node.get('id'), api_key=mdah_api_key)
  File "/usr/lib/pymodules/python2.7/flickrapi/__init__.py", line 337, in handler
    parse_format=args['format'], **args)
  File "/usr/lib/pymodules/python2.7/flickrapi/__init__.py", line 423, in __wrap_in_parser
    return parser(self, data)
  File "/usr/lib/pymodules/python2.7/flickrapi/__init__.py", line 258, in parse_etree
    rsp = ElementTree.fromstring(rest_xml)
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 1301, in XML
    return parser.close()
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 1654, in close
self._raiseerror(v)
  File "/usr/lib/python2.7/xml/etree/ElementTree.py", line 1506, in _raiseerror
    raise err
xml.etree.ElementTree.ParseError: no element found: line 1, column 0

我说随机是因为这个异常会发生在照片处理中不可预测的点。

似乎它是 XML 中的缺失值，或者是可以预测的编码问题，所以我不知道如何解决它。我知道我远远低于每小时通话次数的限制。

# -*- coding: utf-8 -*-

import argparse
import flickrapi
try:
    import xml.etree.cElementTree as ET
except ImportError:
    import xml.etree.ElementTree as ET
import csv

mdah_api_key = 'something'
mdah_api_secret = 'something'

fileencoding = "iso-8859-1"

flickr = flickrapi.FlickrAPI(mdah_api_key, mdah_api_secret)                      

# authorize user
(token, frob) = flickr.get_token_part_one(perms='write')                                                            
if not token: 
   raw_input('Press ENTER after you authorized this program')
flickr.get_token_part_two((token, frob))

photosets_dict = dict()                                                                                                                                         

f = open('flickr-data.csv', 'w')
writer = csv.writer(f)

parser = argparse.ArgumentParser(description='export metadata for Flickr user by set (or all photos if no set specified)')

parser.add_argument('-u','--user', default='something', help='target Flickr user')
parser.add_argument('-p','--photoset', default='all', help='target photoset')
args = parser.parse_args()

def get_photoset_metadata(photoset):

    photoset_info_tree = ET.ElementTree(flickr.photosets_getInfo(api_key=mdah_api_key, photoset_id=photoset))       
    photoset_tree = ET.ElementTree(flickr.photosets_getPhotos(api_key=mdah_api_key, photoset_id=photoset))  

    photo_ids = []  
    data = []
    data_row = []

    for title in photoset_info_tree.iter('title'):
      set_title = title.text.decode(fileencoding)    

    # grab all photo ids in set
    for node in photoset_tree.iter('photo'):

      # get each photo
      photo = flickr.photos_getInfo(photo_id=node.get('id'), api_key=mdah_api_key)
      photo_tree = ET.ElementTree(photo)

      data_row.append(set_title)

      for title in photo_tree.iter('title'):
         data_row.append(title.text.decode(fileencoding))

      try:
         geodata = flickr.photos_geo_getLocation(photo_id=node.get('id'), api_key=mdah_api_key)
         geodata_tree = ET.ElementTree(geodata)

         for geonode in geodata_tree.iter('location'):            
            data_row.append(geonode.get('latitude').decode(fileencoding))
            data_row.append(geonode.get('longitude').decode(fileencoding))
            data_row.append(geonode.get('accuracy').decode(fileencoding))
         for geonode in geodata_tree.iter('country'):
            data_row.append(geonode.text.decode(fileencoding))         
         for geonode in geodata_tree.iter('region'):
            data_row.append(geonode.text.decode(fileencoding))
         for geonode in geodata_tree.iter('county'):
            data_row.append(geonode.text.decode(fileencoding))
         for geonode in geodata_tree.iter('locality'):
            data_row.append(geonode.text.decode(fileencoding))
         for geonode in geodata_tree.iter('neighbourhood'):
            data_row.append(geonode.text.decode(fileencoding))
      except Exception as e:
         e = True

      writer.writerow(data_row)
      print data_row     

      data_row = []

if args.photoset == 'all':
   photosets_tree = ET.ElementTree(flickr.photosets_getList(api_key=mdah_api_key, user_id=args.user))   

   # grab all photosets     
   for node in photosets_tree.iter('photoset'):
      photosets_dict[node.get('id')] = node[0].text

   # iterate over photosets dictionary
   for key, value in photosets_dict.items():
      print '-- Exporting metadata from ' + key + ', ' + value + ' --'
      get_photoset_metadata(key)
else:
   get_photoset_metadata(args.photoset)

这是flickr.photos.getInfoXML 返回的前几行：

<?xml version="1.0" encoding="utf-8" ?>
<rsp stat="ok">
  <photo id="8009597985" secret="something" server="8182" farm="9" dateuploaded="1348248234" isfavorite="0" license="7" safety_level="0" rotation="0" originalsecret="something" originalformat="png" views="97" media="photo">
    <owner nsid="77015680@N05" username="Mississippi Department of Archives and History" realname="" location="" iconserver="5324" iconfarm="6" path_alias="mississippi-dept-of-archives-and-history" />
    <title>Memphis Warehouse Company.</title>
4

0 回答 0