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

Genericise Get_Tracks_Info to take any infiniscrolling list URL

Browse Source
This commit is contained in:
Thomas Wade 2018-09-19 20:48:21 +09:30
parent 33dd9edcdc
commit 8b4c3f5489
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
scrape.py
View File

@ -96,10 +96,10 @@ def Get_Basic_Info(user):
user.like_count = like_count_elem.string.split(' ')[0] user.like_count = like_count_elem.string.split(' ')[0]
print(' Likes: ' + str(user.like_count)) print(' Likes: ' + str(user.like_count))
def Get_Tracks_Info(user): def Get_Tracks_Info(url):
# Get the user's tracks page and soup it # Get the page and soup it
print('GET: https://soundcloud.com/' + user.url_username + '/tracks') print('GET: ' + url)
driver.get('https://soundcloud.com/' + user.url_username + '/tracks') driver.get(url)
# Loop until we reach the bottom of the page so all tracks are loaded # Loop until we reach the bottom of the page so all tracks are loaded
while True: while True:
@ -170,7 +170,7 @@ def Get_Tracks_Info(user):
print(' ' + track.artist + ' - ' + track.title) print(' ' + track.artist + ' - ' + track.title)
user.tracks = tracks return tracks
user_dict = {} user_dict = {}
users_to_process = ['thomotron', 'lacheque', 'slynk', 'bossfightswe'] users_to_process = ['thomotron', 'lacheque', 'slynk', 'bossfightswe']
@ -192,7 +192,7 @@ for user_str in users_to_process:
Get_Basic_Info(user) Get_Basic_Info(user)
# Get their tracks # Get their tracks
Get_Tracks_Info(user) user.tracks = Get_Tracks_Info('https://soundcloud.com/' + user.url_username + '/tracks')
# Finally add the user to the dictionary # Finally add the user to the dictionary
user_dict[user.url_username] = user user_dict[user.url_username] = user