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

Actually use element provided by loop

Browse Source 
*facedesk*
This commit is contained in:
Thomas Wade 2018-09-19 18:37:04 +09:30
parent 8c8631df7c
commit 33dd9edcdc
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
scrape.py
View File

@ -120,18 +120,18 @@ def Get_Tracks_Info(user):
tracks = {} tracks = {}
track_elems = soup.find_all(class_='soundList__item') track_elems = soup.find_all('li', class_='soundList__item')
for track_elem in track_elems: for track_elem in track_elems:
# Initialise a track object to hold our data # Initialise a track object to hold our data
track = Track() track = Track()
# Grab the title # Grab the title
title_elem = soup.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 = title_elem.span.string.strip()
# 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 = soup.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()
@ -140,17 +140,17 @@ def Get_Tracks_Info(user):
continue continue
# Grab when it was uploaded # Grab when it was uploaded
date_elem = soup.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 = date_elem.time['datetime']
# Grab the first tag featured on the list item # Grab the first tag featured on the list item
tag_elem = soup.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 = 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 = soup.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 = elem['title'].split(' ')
@ -160,10 +160,10 @@ def Get_Tracks_Info(user):
track.comments = num track.comments = num
# Grab the like count # Grab the like count
track.likes = soup.find(class_='sc-button-like').string.strip() track.likes = track_elem.find(class_='sc-button-like').string.strip()
# Grab the repost count # Grab the repost count
track.reposts = soup.find(class_='sc-button-repost').string.strip() track.reposts = track_elem.find(class_='sc-button-repost').string.strip()
# Finally add the track to the dictionary # Finally add the track to the dictionary
tracks[track.artist + track.title] = track tracks[track.artist + track.title] = track