Files
media-parser/tests/test_wechat_mp_parser.py
T

219 lines
8.9 KiB
Python

import unittest
from unittest.mock import Mock, patch
from src.parsers.wechat_mp_parser import WechatMpParser
class WechatMpParserTest(unittest.TestCase):
URL = "https://mp.weixin.qq.com/s/test_article_123"
def test_maps_article_response(self):
html_content = """
<!DOCTYPE html>
<html>
<head>
<meta property="og:title" content="测试公众号标题" />
<meta property="og:article:author" content="测试公众号" />
<meta property="og:image" content="https://mmbiz.qpic.cn/cover.jpg" />
</head>
<body>
<script>
var msg_title = '测试公众号标题';
var nickname = '测试公众号';
var user_name = 'gh_123456789abc';
var msg_cdn_url = 'https://mmbiz.qpic.cn/cover.jpg';
</script>
<h1 id="activity-name">测试公众号标题</h1>
<a id="js_name">测试公众号</a>
<div id="js_content">
<p>正文内容</p>
<img data-src="https://mmbiz.qpic.cn/mmbiz_png/test/640?wx_fmt=png" />
<img data-src="https://mmbiz.qpic.cn/mmbiz_jpg/test2/300?wx_fmt=jpeg" />
<mpvoice voice_encode_fileid="voice_file_999" name="语音"></mpvoice>
</div>
</body>
</html>
"""
response = Mock()
response.status_code = 200
response.raise_for_status.return_value = None
response.text = html_content
with patch("requests.Session.get", return_value=response):
parser = WechatMpParser(self.URL)
self.assertEqual(parser.get_title_content(), "测试公众号标题")
self.assertEqual(parser.get_author_info()["nickname"], "测试公众号")
self.assertEqual(parser.get_author_info()["author_id"], "gh_123456789abc")
self.assertEqual(parser.get_cover_photo_url(), "https://mmbiz.qpic.cn/cover.jpg")
self.assertEqual(len(parser.get_image_list()), 2)
self.assertEqual(parser.get_image_list()[0], "https://mmbiz.qpic.cn/mmbiz_png/test/0?wx_fmt=png")
self.assertEqual(parser.get_audio_url(), "https://res.wx.qq.com/voice/getvoice?mediaid=voice_file_999")
def test_maps_video_response(self):
html_content = """
<!DOCTYPE html>
<html>
<body>
<script>
window.cgiData = {
title: '测试视频标题',
user_name: 'gh_video123',
nick_name: '视频号博主',
round_head_img: 'https://mmbiz.qpic.cn/avatar.png',
cdn_url: 'https://mmbiz.qpic.cn/cover.jpg',
};
video_page_info = {
mp_video_trans_info: [
{
format_id: 10004,
width: 480,
height: 854,
filesize: 1000,
video_quality_level: 1,
url: 'http://mpvideo.qpic.cn/video_low.mp4?k=1'
},
{
format_id: 10002,
width: 1080,
height: 1920,
filesize: 5000,
video_quality_level: 3,
url: 'http://mpvideo.qpic.cn/video_hd.mp4?k=2&amp;p=1'
}
]
};
</script>
</body>
</html>
"""
response = Mock()
response.status_code = 200
response.raise_for_status.return_value = None
response.text = html_content
with patch("requests.Session.get", return_value=response):
parser = WechatMpParser(self.URL)
self.assertEqual(parser.get_title_content(), "测试视频标题")
self.assertEqual(parser.get_author_info()["nickname"], "视频号博主")
self.assertEqual(parser.get_author_info()["author_id"], "gh_video123")
self.assertEqual(parser.get_author_info()["avatar"], "https://mmbiz.qpic.cn/avatar.png")
self.assertEqual(parser.get_real_video_url(), "http://mpvideo.qpic.cn/video_hd.mp4?k=2&p=1")
self.assertEqual(parser.get_video_list(), ["http://mpvideo.qpic.cn/video_hd.mp4?k=2&p=1"])
def test_maps_multiple_videos_response(self):
html_content = """
<!DOCTYPE html>
<html>
<head>
<meta property="og:title" content="多视频文章测试" />
</head>
<body>
<script>
var videoPageInfos = [
{
video_id: 'wxv_video_1',
mp_video_trans_info: [
{
format_id: 10004,
width: 480,
height: 854,
filesize: 1000,
video_quality_level: 1,
url: 'http://mpvideo.qpic.cn/0bc3vid1aaaa.f10004.mp4?k=1'
},
{
format_id: 10002,
width: 1080,
height: 1920,
filesize: 5000,
video_quality_level: 3,
url: 'http://mpvideo.qpic.cn/0bc3vid1aaaa.f10002.mp4?k=2'
}
]
},
{
video_id: 'wxv_video_2',
mp_video_trans_info: [
{
format_id: 10004,
width: 640,
height: 360,
filesize: 2000,
video_quality_level: 1,
url: 'http://mpvideo.qpic.cn/0bc3vid2bbbb.f10004.mp4?k=3'
},
{
format_id: 10002,
width: 1280,
height: 720,
filesize: 6000,
video_quality_level: 3,
url: 'http://mpvideo.qpic.cn/0bc3vid2bbbb.f10002.mp4?k=4'
}
]
}
];
</script>
</body>
</html>
"""
response = Mock()
response.status_code = 200
response.raise_for_status.return_value = None
response.text = html_content
with patch("requests.Session.get", return_value=response):
parser = WechatMpParser(self.URL)
self.assertEqual(parser.get_title_content(), "多视频文章测试")
self.assertEqual(parser.get_real_video_url(), "http://mpvideo.qpic.cn/0bc3vid1aaaa.f10002.mp4?k=2")
self.assertEqual(
parser.get_video_list(),
[
"http://mpvideo.qpic.cn/0bc3vid1aaaa.f10002.mp4?k=2",
"http://mpvideo.qpic.cn/0bc3vid2bbbb.f10002.mp4?k=4",
],
)
def test_handles_request_failure_gracefully(self):
response = Mock()
response.raise_for_status.side_effect = Exception("HTTP 404")
with patch("requests.Session.get", return_value=response):
parser = WechatMpParser(self.URL)
self.assertEqual(parser.get_title_content(), "微信公众号文章")
self.assertEqual(parser.get_image_list(), [])
self.assertIsNone(parser.get_real_video_url())
self.assertEqual(parser.get_video_list(), [])
def test_detects_environment_verify_page(self):
response = Mock()
response.raise_for_status.return_value = None
response.text = '<html><head><link rel="stylesheet" href="//res.wx.qq.com/secitptpage/verify.css"></head><body><h2 class="weui-msg__title">环境异常</h2><p>当前环境异常,完成验证后即可继续访问。</p></body></html>'
with patch("requests.Session.get", return_value=response):
parser = WechatMpParser(self.URL)
self.assertIsNotNone(parser.terminal_error)
self.assertEqual(parser.terminal_error["error_code"], "WECHAT_MP_VERIFY_REQUIRED")
def test_detects_deleted_article(self):
response = Mock()
response.raise_for_status.return_value = None
response.text = '<html><body><h3>该内容已被发布者删除</h3></body></html>'
with patch("requests.Session.get", return_value=response):
parser = WechatMpParser(self.URL)
self.assertIsNotNone(parser.terminal_error)
self.assertEqual(parser.terminal_error["error_code"], "MEDIA_DELETED_OR_PRIVATE")
if __name__ == "__main__":
unittest.main()