Merge branch 'modular-data-extract'

Commits in this branch are prefixed with "Extraction:"
This branch refactors data extraction. All such functionality has been moved to the yt_data_extract module.
Responses from requests are given to the module and it parses them into a consistent, more useful format.
The dependency on youtube-dl has also been dropped and this functionality has been built from scratch for these reasons:
(1) I've noticed youtube-dl breaks more often than invidious (which uses watch page extraction built from scratch) in response to changes from Youtube, so I'm hoping what I wrote will also be less brittle.
(2) Such breakage is inconvenient because I have to manually merge the fixes since I had to make changes to youtube-dl to make it do things such as extracting related videos.
(3) I have no control over error handling and request pooling with youtube-dl, since it does all the requests (these would require intrusive changes I don't want to maintain).
(4) I will now be able to finally display the number of comments and whether comments are disabled without making additional requests.

1 files changed, 0 insertions, 80 deletions

diff --git a/youtube_dl/downloader/dash.py b/youtube_dl/downloader/dash.py
deleted file mode 100644
index eaa7adf..0000000
--- a/youtube_dl/downloader/dash.py
+++ /dev/null
@@ -1,80 +0,0 @@
-from __future__ import unicode_literals
-
-from .fragment import FragmentFD
-from ..compat import compat_urllib_error
-from ..utils import (
-    DownloadError,
-    urljoin,
-)
-
-
-class DashSegmentsFD(FragmentFD):
-    """
-    Download segments in a DASH manifest
-    """
-
-    FD_NAME = 'dashsegments'
-
-    def real_download(self, filename, info_dict):
-        fragment_base_url = info_dict.get('fragment_base_url')
-        fragments = info_dict['fragments'][:1] if self.params.get(
-            'test', False) else info_dict['fragments']
-
-        ctx = {
-            'filename': filename,
-            'total_frags': len(fragments),
-        }
-
-        self._prepare_and_start_frag_download(ctx)
-
-        fragment_retries = self.params.get('fragment_retries', 0)
-        skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
-
-        frag_index = 0
-        for i, fragment in enumerate(fragments):
-            frag_index += 1
-            if frag_index <= ctx['fragment_index']:
-                continue
-            # In DASH, the first segment contains necessary headers to
-            # generate a valid MP4 file, so always abort for the first segment
-            fatal = i == 0 or not skip_unavailable_fragments
-            count = 0
-            while count <= fragment_retries:
-                try:
-                    fragment_url = fragment.get('url')
-                    if not fragment_url:
-                        assert fragment_base_url
-                        fragment_url = urljoin(fragment_base_url, fragment['path'])
-                    success, frag_content = self._download_fragment(ctx, fragment_url, info_dict)
-                    if not success:
-                        return False
-                    self._append_fragment(ctx, frag_content)
-                    break
-                except compat_urllib_error.HTTPError as err:
-                    # YouTube may often return 404 HTTP error for a fragment causing the
-                    # whole download to fail. However if the same fragment is immediately
-                    # retried with the same request data this usually succeeds (1-2 attemps
-                    # is usually enough) thus allowing to download the whole file successfully.
-                    # To be future-proof we will retry all fragments that fail with any
-                    # HTTP error.
-                    count += 1
-                    if count <= fragment_retries:
-                        self.report_retry_fragment(err, frag_index, count, fragment_retries)
-                except DownloadError:
-                    # Don't retry fragment if error occurred during HTTP downloading
-                    # itself since it has own retry settings
-                    if not fatal:
-                        self.report_skip_fragment(frag_index)
-                        break
-                    raise
-
-            if count > fragment_retries:
-                if not fatal:
-                    self.report_skip_fragment(frag_index)
-                    continue
-                self.report_error('giving up after %s fragment retries' % fragment_retries)
-                return False
-
-        self._finish_frag_download(ctx)
-
-        return True