From 71df9b7fd504767583cf1e088ae307c942799f2b Mon Sep 17 00:00:00 2001 From: pukkandan Date: Wed, 30 Nov 2022 11:34:51 +0530 Subject: [PATCH] [cleanup] Misc --- .github/workflows/core.yml | 11 ++++++----- .github/workflows/quick-test.yml | 13 ++++++------- .gitignore | 1 + CONTRIBUTING.md | 22 +++++++++++++++++++--- README.md | 26 +++++++++++++------------- yt_dlp/YoutubeDL.py | 2 +- yt_dlp/__init__.py | 7 +++---- yt_dlp/downloader/common.py | 5 ++++- yt_dlp/extractor/common.py | 12 +++++++++++- yt_dlp/options.py | 8 ++++---- yt_dlp/utils.py | 5 ++++- 11 files changed, 72 insertions(+), 40 deletions(-) diff --git a/.github/workflows/core.yml b/.github/workflows/core.yml index e12918626..dead444c0 100644 --- a/.github/workflows/core.yml +++ b/.github/workflows/core.yml @@ -12,13 +12,13 @@ jobs: fail-fast: false matrix: os: [ubuntu-latest] - # CPython 3.9 is in quick-test - python-version: ['3.7', '3.10', 3.11-dev, pypy-3.7, pypy-3.8] + # CPython 3.11 is in quick-test + python-version: ['3.8', '3.9', '3.10', pypy-3.7, pypy-3.8] run-tests-ext: [sh] include: # atleast one of each CPython/PyPy tests must be in windows - os: windows-latest - python-version: '3.8' + python-version: '3.7' run-tests-ext: bat - os: windows-latest python-version: pypy-3.9 @@ -33,5 +33,6 @@ jobs: run: pip install pytest - name: Run tests continue-on-error: False - run: ./devscripts/run_tests.${{ matrix.run-tests-ext }} core - # Linter is in quick-test + run: | + python3 -m yt_dlp -v || true # Print debug head + ./devscripts/run_tests.${{ matrix.run-tests-ext }} core diff --git a/.github/workflows/quick-test.yml b/.github/workflows/quick-test.yml index 8a0ac98bb..930e58152 100644 --- a/.github/workflows/quick-test.yml +++ b/.github/workflows/quick-test.yml @@ -10,24 +10,23 @@ jobs: runs-on: ubuntu-latest steps: - uses: actions/checkout@v3 - - name: Set up Python + - name: Set up Python 3.11 uses: actions/setup-python@v4 with: - python-version: 3.9 + python-version: '3.11' - name: Install test requirements run: pip install pytest pycryptodomex - name: Run tests - run: ./devscripts/run_tests.sh core + run: | + python3 -m yt_dlp -v || true + ./devscripts/run_tests.sh core flake8: name: Linter if: "!contains(github.event.head_commit.message, 'ci skip all')" runs-on: ubuntu-latest steps: - uses: actions/checkout@v3 - - name: Set up Python - uses: actions/setup-python@v4 - with: - python-version: 3.9 + - uses: actions/setup-python@v4 - name: Install flake8 run: pip install flake8 - name: Make lazy extractors diff --git a/.gitignore b/.gitignore index 0ce059b34..00d74057f 100644 --- a/.gitignore +++ b/.gitignore @@ -71,6 +71,7 @@ dist/ zip/ tmp/ venv/ +.venv/ completions/ # Misc diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index a8ac671dc..551db674e 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -351,8 +351,9 @@ Say you extracted a list of thumbnails into `thumbnail_data` and want to iterate ```python thumbnail_data = data.get('thumbnails') or [] thumbnails = [{ - 'url': item['url'] -} for item in thumbnail_data] # correct + 'url': item['url'], + 'height': item.get('h'), +} for item in thumbnail_data if item.get('url')] # correct ``` and not like: @@ -360,12 +361,27 @@ and not like: ```python thumbnail_data = data.get('thumbnails') thumbnails = [{ - 'url': item['url'] + 'url': item['url'], + 'height': item.get('h'), } for item in thumbnail_data] # incorrect ``` In this case, `thumbnail_data` will be `None` if the field was not found and this will cause the loop `for item in thumbnail_data` to raise a fatal error. Using `or []` avoids this error and results in setting an empty list in `thumbnails` instead. +Alternately, this can be further simplified by using `traverse_obj` + +```python +thumbnails = [{ + 'url': item['url'], + 'height': item.get('h'), +} for item in traverse_obj(data, ('thumbnails', lambda _, v: v['url']))] +``` + +or, even better, + +```python +thumbnails = traverse_obj(data, ('thumbnails', ..., {'url': 'url', 'height': 'h'})) +``` ### Provide fallbacks diff --git a/README.md b/README.md index fa55d130b..b6a07da9a 100644 --- a/README.md +++ b/README.md @@ -432,19 +432,19 @@ You can also fork the project on GitHub and run your fork's [build workflow](.gi explicitly provided IP block in CIDR notation ## Video Selection: - -I, --playlist-items ITEM_SPEC Comma separated playlist_index of the videos + -I, --playlist-items ITEM_SPEC Comma separated playlist_index of the items to download. You can specify a range using "[START]:[STOP][:STEP]". For backward compatibility, START-STOP is also supported. Use negative indices to count from the right and negative STEP to download in reverse order. E.g. "-I 1:3,7,-5::2" used on a - playlist of size 15 will download the videos + playlist of size 15 will download the items at index 1,2,3,7,11,13,15 - --min-filesize SIZE Do not download any videos smaller than + --min-filesize SIZE Abort download if filesize is smaller than + SIZE, e.g. 50k or 44.6M + --max-filesize SIZE Abort download if filesize is larger than SIZE, e.g. 50k or 44.6M - --max-filesize SIZE Do not download any videos larger than SIZE, - e.g. 50k or 44.6M --date DATE Download only videos uploaded on this date. The date can be "YYYYMMDD" or in the format [now|today|yesterday][-N[day|week|month|year]]. @@ -491,9 +491,9 @@ You can also fork the project on GitHub and run your fork's [build workflow](.gi a file that is in the archive --break-on-reject Stop the download process when encountering a file that has been filtered out - --break-per-input --break-on-existing, --break-on-reject, - --max-downloads, and autonumber resets per - input URL + --break-per-input Alters --max-downloads, --break-on-existing, + --break-on-reject, and autonumber to reset + per input URL --no-break-per-input --break-on-existing and similar options terminates the entire download queue --skip-playlist-after-errors N Number of allowed failures until the rest of @@ -1046,10 +1046,10 @@ Make chapter entries for, or remove various segments (sponsor, for, separated by commas. Available categories are sponsor, intro, outro, selfpromo, preview, filler, interaction, - music_offtopic, poi_highlight, chapter, all and - default (=all). You can prefix the category - with a "-" to exclude it. See [1] for - description of the categories. E.g. + music_offtopic, poi_highlight, chapter, all + and default (=all). You can prefix the + category with a "-" to exclude it. See [1] + for description of the categories. E.g. --sponsorblock-mark all,-preview [1] https://wiki.sponsor.ajay.app/w/Segment_Categories --sponsorblock-remove CATS SponsorBlock categories to be removed from @@ -1058,7 +1058,7 @@ Make chapter entries for, or remove various segments (sponsor, remove takes precedence. The syntax and available categories are the same as for --sponsorblock-mark except that "default" - refers to "all,-filler" and poi_highlight and + refers to "all,-filler" and poi_highlight, chapter are not available --sponsorblock-chapter-title TEMPLATE An output template for the title of the diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py index b1d009280..8d28783d8 100644 --- a/yt_dlp/YoutubeDL.py +++ b/yt_dlp/YoutubeDL.py @@ -3123,7 +3123,7 @@ class YoutubeDL: fd, success = None, True if info_dict.get('protocol') or info_dict.get('url'): fd = get_suitable_downloader(info_dict, self.params, to_stdout=temp_filename == '-') - if fd is not FFmpegFD and ( + if fd is not FFmpegFD and 'no-direct-merge' not in self.params['compat_opts'] and ( info_dict.get('section_start') or info_dict.get('section_end')): msg = ('This format cannot be partially downloaded' if FFmpegFD.available() else 'You have requested downloading the video partially, but ffmpeg is not installed') diff --git a/yt_dlp/__init__.py b/yt_dlp/__init__.py index f1a347514..f1d6c369b 100644 --- a/yt_dlp/__init__.py +++ b/yt_dlp/__init__.py @@ -91,12 +91,11 @@ def get_urls(urls, batchfile, verbose): def print_extractor_information(opts, urls): - # Importing GenericIE is currently slow since it imports other extractors - # TODO: Move this back to module level after generalization of embed detection - from .extractor.generic import GenericIE - out = '' if opts.list_extractors: + # Importing GenericIE is currently slow since it imports YoutubeIE + from .extractor.generic import GenericIE + urls = dict.fromkeys(urls, False) for ie in list_extractor_classes(opts.age_limit): out += ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie.working() else '') + '\n' diff --git a/yt_dlp/downloader/common.py b/yt_dlp/downloader/common.py index fe3633250..077b29b41 100644 --- a/yt_dlp/downloader/common.py +++ b/yt_dlp/downloader/common.py @@ -20,6 +20,7 @@ from ..utils import ( RetryManager, classproperty, decodeArgument, + deprecation_warning, encodeFilename, format_bytes, join_nonempty, @@ -180,7 +181,9 @@ class FileDownloader: @staticmethod def parse_bytes(bytestr): """Parse a string indicating a byte quantity into an integer.""" - parse_bytes(bytestr) + deprecation_warning('yt_dlp.FileDownloader.parse_bytes is deprecated and ' + 'may be removed in the future. Use yt_dlp.utils.parse_bytes instead') + return parse_bytes(bytestr) def slow_down(self, start_time, now, byte_counter): """Sleep if the download speed is over the rate limit.""" diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index 3ca8fe24c..3910c55ad 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -71,6 +71,7 @@ from ..utils import ( str_to_int, strip_or_none, traverse_obj, + truncate_string, try_call, try_get, unescapeHTML, @@ -674,7 +675,8 @@ class InfoExtractor: for _ in range(2): try: self.initialize() - self.write_debug('Extracting URL: %s' % url) + self.to_screen('Extracting URL: %s' % ( + url if self.get_param('verbose') else truncate_string(url, 100, 20))) ie_result = self._real_extract(url) if ie_result is None: return None @@ -1906,6 +1908,14 @@ class InfoExtractor: errnote=None, fatal=True, live=False, data=None, headers={}, query={}): + if not m3u8_url: + if errnote is not False: + errnote = errnote or 'Failed to obtain m3u8 URL' + if fatal: + raise ExtractorError(errnote, video_id=video_id) + self.report_warning(f'{errnote}{bug_reports_message()}') + return [], {} + res = self._download_webpage_handle( m3u8_url, video_id, note='Downloading m3u8 information' if note is None else note, diff --git a/yt_dlp/options.py b/yt_dlp/options.py index bee867aa9..bc574b885 100644 --- a/yt_dlp/options.py +++ b/yt_dlp/options.py @@ -535,10 +535,10 @@ def create_parser(): '-I', '--playlist-items', dest='playlist_items', metavar='ITEM_SPEC', default=None, help=( - 'Comma separated playlist_index of the videos to download. ' + 'Comma separated playlist_index of the items to download. ' 'You can specify a range using "[START]:[STOP][:STEP]". For backward compatibility, START-STOP is also supported. ' 'Use negative indices to count from the right and negative STEP to download in reverse order. ' - 'E.g. "-I 1:3,7,-5::2" used on a playlist of size 15 will download the videos at index 1,2,3,7,11,13,15')) + 'E.g. "-I 1:3,7,-5::2" used on a playlist of size 15 will download the items at index 1,2,3,7,11,13,15')) selection.add_option( '--match-title', dest='matchtitle', metavar='REGEX', @@ -554,7 +554,7 @@ def create_parser(): selection.add_option( '--max-filesize', metavar='SIZE', dest='max_filesize', default=None, - help='Abort download if filesize if larger than SIZE, e.g. 50k or 44.6M') + help='Abort download if filesize is larger than SIZE, e.g. 50k or 44.6M') selection.add_option( '--date', metavar='DATE', dest='date', default=None, @@ -635,7 +635,7 @@ def create_parser(): selection.add_option( '--break-per-input', action='store_true', dest='break_per_url', default=False, - help='--break-on-existing, --break-on-reject, --max-downloads, and autonumber resets per input URL') + help='Alters --max-downloads, --break-on-existing, --break-on-reject, and autonumber to reset per input URL') selection.add_option( '--no-break-per-input', action='store_false', dest='break_per_url', diff --git a/yt_dlp/utils.py b/yt_dlp/utils.py index ed1b24335..a3da3c69e 100644 --- a/yt_dlp/utils.py +++ b/yt_dlp/utils.py @@ -3872,6 +3872,9 @@ class download_range_func: return (isinstance(other, download_range_func) and self.chapters == other.chapters and self.ranges == other.ranges) + def __repr__(self): + return f'{type(self).__name__}({self.chapters}, {self.ranges})' + def parse_dfxp_time_expr(time_expr): if not time_expr: @@ -5976,7 +5979,7 @@ def truncate_string(s, left, right=0): assert left > 3 and right >= 0 if s is None or len(s) <= left + right: return s - return f'{s[:left-3]}...{s[-right:]}' + return f'{s[:left-3]}...{s[-right:] if right else ""}' def orderedSet_from_options(options, alias_dict, *, use_regex=False, start=None):