yt_dlp/extractor/esri.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_urlparse
   5 from ..utils import (
   6     int_or_none,
   7     parse_filesize,
   8     unified_strdate,
   9 )
  10
  11
  12 class EsriVideoIE(InfoExtractor):
  13     _VALID_URL = r'https?://video\.esri\.com/watch/(?P<id>[0-9]+)'
  14     _TEST = {
  15         'url': 'https://video.esri.com/watch/1124/arcgis-online-_dash_-developing-applications',
  16         'md5': 'd4aaf1408b221f1b38227a9bbaeb95bc',
  17         'info_dict': {
  18             'id': '1124',
  19             'ext': 'mp4',
  20             'title': 'ArcGIS Online - Developing Applications',
  21             'description': 'Jeremy Bartley demonstrates how to develop applications with ArcGIS Online.',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'duration': 185,
  24             'upload_date': '20120419',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         formats = []
  34         for width, height, content in re.findall(
  35                 r'(?s)<li><strong>(\d+)x(\d+):</strong>(.+?)</li>', webpage):
  36             for video_url, ext, filesize in re.findall(
  37                     r'<a[^>]+href="([^"]+)">([^<]+)&nbsp;\(([^<]+)\)</a>', content):
  38                 formats.append({
  39                     'url': compat_urlparse.urljoin(url, video_url),
  40                     'ext': ext.lower(),
  41                     'format_id': '%s-%s' % (ext.lower(), height),
  42                     'width': int(width),
  43                     'height': int(height),
  44                     'filesize_approx': parse_filesize(filesize),
  45                 })
  46
  47         title = self._html_search_meta('title', webpage, 'title')
  48         description = self._html_search_meta(
  49             'description', webpage, 'description', fatal=False)
  50
  51         thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail', fatal=False)
  52         if thumbnail:
  53             thumbnail = re.sub(r'_[st]\.jpg$', '_x.jpg', thumbnail)
  54
  55         duration = int_or_none(self._search_regex(
  56             [r'var\s+videoSeconds\s*=\s*(\d+)', r"'duration'\s*:\s*(\d+)"],
  57             webpage, 'duration', fatal=False))
  58
  59         upload_date = unified_strdate(self._html_search_meta(
  60             'last-modified', webpage, 'upload date', fatal=False))
  61
  62         return {
  63             'id': video_id,
  64             'title': title,
  65             'description': description,
  66             'thumbnail': thumbnail,
  67             'duration': duration,
  68             'upload_date': upload_date,
  69             'formats': formats
  70         }