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, 48 deletions

diff --git a/youtube_dl/postprocessor/metadatafromtitle.py b/youtube_dl/postprocessor/metadatafromtitle.py
deleted file mode 100644
index f5c14d9..0000000
--- a/youtube_dl/postprocessor/metadatafromtitle.py
+++ /dev/null
@@ -1,48 +0,0 @@
-from __future__ import unicode_literals
-
-import re
-
-from .common import PostProcessor
-
-
-class MetadataFromTitlePP(PostProcessor):
-    def __init__(self, downloader, titleformat):
-        super(MetadataFromTitlePP, self).__init__(downloader)
-        self._titleformat = titleformat
-        self._titleregex = (self.format_to_regex(titleformat)
-                            if re.search(r'%\(\w+\)s', titleformat)
-                            else titleformat)
-
-    def format_to_regex(self, fmt):
-        r"""
-        Converts a string like
-           '%(title)s - %(artist)s'
-        to a regex like
-           '(?P<title>.+)\ \-\ (?P<artist>.+)'
-        """
-        lastpos = 0
-        regex = ''
-        # replace %(..)s with regex group and escape other string parts
-        for match in re.finditer(r'%\((\w+)\)s', fmt):
-            regex += re.escape(fmt[lastpos:match.start()])
-            regex += r'(?P<' + match.group(1) + '>.+)'
-            lastpos = match.end()
-        if lastpos < len(fmt):
-            regex += re.escape(fmt[lastpos:])
-        return regex
-
-    def run(self, info):
-        title = info['title']
-        match = re.match(self._titleregex, title)
-        if match is None:
-            self._downloader.to_screen(
-                '[fromtitle] Could not interpret title of video as "%s"'
-                % self._titleformat)
-            return [], info
-        for attribute, value in match.groupdict().items():
-            info[attribute] = value
-            self._downloader.to_screen(
-                '[fromtitle] parsed %s: %s'
-                % (attribute, value if value is not None else 'NA'))
-
-        return [], info