diff options
| author | James Taylor <user234683@users.noreply.github.com> | 2019-12-24 13:07:12 -0800 |
|---|---|---|
| committer | James Taylor <user234683@users.noreply.github.com> | 2019-12-24 13:07:12 -0800 |
| commit | 3200d66d880d72ba2c4e687840d31c9c98c66f6a (patch) | |
| tree | f293fec931ee26e4b18f1f6c16e23f4a88a35469 | |
| parent | a428d47bde199a3837dcc0208cb240a1dac61992 (diff) | |
| download | yt-local-3200d66d880d72ba2c4e687840d31c9c98c66f6a.tar.lz yt-local-3200d66d880d72ba2c4e687840d31c9c98c66f6a.tar.xz yt-local-3200d66d880d72ba2c4e687840d31c9c98c66f6a.zip | |
Fix extract_approx_int not working for non-approx ints, make extract_int more robust
For example, "354 subscribers" wasn't being extracted correctly be extract_approx_int.
Make extract_approx_int and extract_int only extract integers that are words.
So e.g. 342 will not be extracted from internetuser342
| -rw-r--r-- | youtube/yt_data_extract/common.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/youtube/yt_data_extract/common.py b/youtube/yt_data_extract/common.py index 06f0e95..4af76c2 100644 --- a/youtube/yt_data_extract/common.py +++ b/youtube/yt_data_extract/common.py @@ -135,7 +135,7 @@ def extract_int(string, default=None): string = extract_str(string) if not string: return default - match = re.search(r'(\d+)', string.replace(',', '')) + match = re.search(r'\b(\d+)\b', string.replace(',', '')) if match is None: return default try: @@ -149,7 +149,7 @@ def extract_approx_int(string): string = extract_str(string) if not string: return None - match = re.search(r'(\d+(?:\.\d+)?[KMBTkmbt])', string.replace(',', '')) + match = re.search(r'\b(\d+(?:\.\d+)?[KMBTkmbt]?)\b', string.replace(',', '')) if match is None: return None return match.group(1) |