test/test_write_annotations.py

   1 #!/usr/bin/env python
   2 # coding: utf-8
   3
   4 import xml.etree.ElementTree
   5 import os
   6 import sys
   7 import unittest
   8
   9 # Allow direct execution
  10 sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
  11
  12 import youtube_dl.YoutubeDL
  13 import youtube_dl.extractor
  14 from youtube_dl.utils import *
  15 from .helper import try_rm
  16
  17 PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
  18
  19 # General configuration (from __init__, not very elegant...)
  20 jar = compat_cookiejar.CookieJar()
  21 cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
  22 proxy_handler = compat_urllib_request.ProxyHandler()
  23 opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
  24 compat_urllib_request.install_opener(opener)
  25
  26 class YoutubeDL(youtube_dl.YoutubeDL):
  27     def __init__(self, *args, **kwargs):
  28         super(YoutubeDL, self).__init__(*args, **kwargs)
  29         self.to_stderr = self.to_screen
  30
  31 with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
  32     params = json.load(pf)
  33 params['writeannotations'] = True
  34 params['skip_download'] = True
  35 params['writeinfojson'] = False
  36 params['format'] = 'flv'
  37
  38 TEST_ID = 'gr51aVj-mLg'
  39 ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
  40 EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
  41
  42 class TestAnnotations(unittest.TestCase):
  43     def setUp(self):
  44         # Clear old files
  45         self.tearDown()
  46
  47
  48     def test_info_json(self):
  49         expected = list(EXPECTED_ANNOTATIONS) #Two annotations could have the same text.
  50         ie = youtube_dl.extractor.YoutubeIE()
  51         ydl = YoutubeDL(params)
  52         ydl.add_info_extractor(ie)
  53         ydl.download([TEST_ID])
  54         self.assertTrue(os.path.exists(ANNOTATIONS_FILE))
  55         annoxml = None
  56         with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
  57                 annoxml = xml.etree.ElementTree.parse(annof)
  58         self.assertTrue(annoxml is not None, 'Failed to parse annotations XML')
  59         root = annoxml.getroot()
  60         self.assertEqual(root.tag, 'document')
  61         annotationsTag = root.find('annotations')
  62         self.assertEqual(annotationsTag.tag, 'annotations')
  63         annotations = annotationsTag.findall('annotation')
  64
  65         #Not all the annotations have TEXT children and the annotations are returned unsorted.
  66         for a in annotations:
  67                 self.assertEqual(a.tag, 'annotation')
  68                 if a.get('type') == 'text':
  69                         textTag = a.find('TEXT')
  70                         text = textTag.text
  71                         self.assertTrue(text in expected) #assertIn only added in python 2.7
  72                         #remove the first occurance, there could be more than one annotation with the same text
  73                         expected.remove(text)
  74         #We should have seen (and removed) all the expected annotation texts.
  75         self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')
  76
  77
  78     def tearDown(self):
  79         try_rm(ANNOTATIONS_FILE)
  80
  81 if __name__ == '__main__':
  82     unittest.main()