tom/soundcloud-scrape
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Organise tracks by url rather than artist-author mishmash

Browse Source
This commit is contained in:
Thomas Wade 2018-09-25 17:23:53 +09:30
parent fa9517a21d
commit 9e9a56386f
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
scrape.py
View File

@ -146,15 +146,15 @@ def Get_Tracks_Info(url, limit = 100):
track.title = title_elem.span.string.strip() track.title = title_elem.span.string.strip()
track.url = 'https://soundcloud.com' + title_elem['href'] track.url = 'https://soundcloud.com' + title_elem['href']
# Check if we have already gotten this track before
if track.url in tracks.keys():
continue
# Grab who uploaded it (usually the artist unless it's a label) # Grab who uploaded it (usually the artist unless it's a label)
artist_elem = track_elem.find(class_='soundTitle__usernameText') artist_elem = track_elem.find(class_='soundTitle__usernameText')
if artist_elem: if artist_elem:
track.artist = artist_elem.string.strip() track.artist = artist_elem.string.strip()
# Check if we have already gotten this track before
if str(track.artist) + str(track.title) in tracks.keys():
continue
# Grab when it was uploaded # Grab when it was uploaded
date_elem = track_elem.find(class_='soundTitle__uploadTime') date_elem = track_elem.find(class_='soundTitle__uploadTime')
if date_elem: if date_elem:
@ -186,7 +186,7 @@ def Get_Tracks_Info(url, limit = 100):
track.reposts = repost_elem.string.strip() track.reposts = repost_elem.string.strip()
# Finally add the track to the dictionary # Finally add the track to the dictionary
tracks[track.artist + track.title] = track tracks[track.url] = track
print(' ' + track.artist + ' - ' + track.title) print(' ' + track.artist + ' - ' + track.title)