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

Flatten all track properties to strings

Browse Source
This commit is contained in:
Thomas Wade 2018-09-27 16:54:40 +09:30
parent 4e14ce2235
commit f3d171a92b
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
scrape.py
View File

@ -173,7 +173,7 @@ def Get_Tracks_Info(url, limit = 100):
# Grab the title and url # Grab the title and url
title_elem = track_elem.find(class_='soundTitle__title') title_elem = track_elem.find(class_='soundTitle__title')
if title_elem: if title_elem:
track.title = title_elem.span.string.strip() track.title = str(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 # Check if we have already gotten this track before
@ -183,23 +183,23 @@ def Get_Tracks_Info(url, limit = 100):
# 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 = str(artist_elem.string.strip())
# 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:
track.date = date_elem.time['datetime'] track.date = str(date_elem.time['datetime'])
# Grab the first tag featured on the list item # Grab the first tag featured on the list item
tag_elem = track_elem.find(class_='soundTitle__tagContent') tag_elem = track_elem.find(class_='soundTitle__tagContent')
if tag_elem: if tag_elem:
track.tag = tag_elem.string track.tag = str(tag_elem.string)
# Grab the play and comment counts (either of these may or may not be present) # Grab the play and comment counts (either of these may or may not be present)
play_comment_elems = track_elem.find_all(class_='sc-ministats-item') play_comment_elems = track_elem.find_all(class_='sc-ministats-item')
if play_comment_elems: if play_comment_elems:
for elem in play_comment_elems: for elem in play_comment_elems:
num, unit = elem['title'].split(' ') num, unit = str(elem['title']).split(' ')
if unit == 'plays': if unit == 'plays':
track.plays = num track.plays = num
elif unit == 'comments': elif unit == 'comments':
@ -208,12 +208,12 @@ def Get_Tracks_Info(url, limit = 100):
# Grab the like count # Grab the like count
like_elem = track_elem.find(class_='sc-button-like') like_elem = track_elem.find(class_='sc-button-like')
if like_elem: if like_elem:
track.likes = like_elem.string.strip() track.likes = str(like_elem.string.strip())
# Grab the repost count # Grab the repost count
repost_elem = track_elem.find(class_='sc-button-repost') repost_elem = track_elem.find(class_='sc-button-repost')
if repost_elem: if repost_elem:
track.reposts = repost_elem.string.strip() track.reposts = str(repost_elem.string.strip())
# Finally add the track to the dictionary # Finally add the track to the dictionary
tracks[track.url] = track tracks[track.url] = track