ytdl/test/test_write_annotations.py

79 lines
2.5 KiB
Python
Raw Normal View History

#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
2013-11-25 03:47:32 +01:00
from test.helper import get_params, try_rm
import io
import xml.etree.ElementTree
import youtube_dl.YoutubeDL
import youtube_dl.extractor
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
super(YoutubeDL, self).__init__(*args, **kwargs)
self.to_stderr = self.to_screen
params = get_params({
'writeannotations': True,
'skip_download': True,
'writeinfojson': False,
'format': 'flv',
})
TEST_ID = 'gr51aVj-mLg'
ANNOTATIONS_FILE = TEST_ID + '.annotations.xml'
EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
2014-11-23 20:41:03 +01:00
class TestAnnotations(unittest.TestCase):
def setUp(self):
# Clear old files
self.tearDown()
def test_info_json(self):
2014-11-23 20:41:03 +01:00
expected = list(EXPECTED_ANNOTATIONS) # Two annotations could have the same text.
ie = youtube_dl.extractor.YoutubeIE()
ydl = YoutubeDL(params)
ydl.add_info_extractor(ie)
ydl.download([TEST_ID])
self.assertTrue(os.path.exists(ANNOTATIONS_FILE))
annoxml = None
with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
2014-11-23 20:41:03 +01:00
annoxml = xml.etree.ElementTree.parse(annof)
self.assertTrue(annoxml is not None, 'Failed to parse annotations XML')
root = annoxml.getroot()
self.assertEqual(root.tag, 'document')
annotationsTag = root.find('annotations')
self.assertEqual(annotationsTag.tag, 'annotations')
annotations = annotationsTag.findall('annotation')
2014-11-23 20:41:03 +01:00
# Not all the annotations have TEXT children and the annotations are returned unsorted.
for a in annotations:
2014-11-23 20:41:03 +01:00
self.assertEqual(a.tag, 'annotation')
if a.get('type') == 'text':
textTag = a.find('TEXT')
text = textTag.text
self.assertTrue(text in expected) # assertIn only added in python 2.7
2016-01-10 16:17:47 +01:00
# remove the first occurrence, there could be more than one annotation with the same text
2014-11-23 20:41:03 +01:00
expected.remove(text)
# We should have seen (and removed) all the expected annotation texts.
self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')
def tearDown(self):
try_rm(ANNOTATIONS_FILE)
if __name__ == '__main__':
unittest.main()