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

Use User class instead of dictionary

Browse Source
This commit is contained in:
Thomas Wade 2018-09-18 17:38:48 +09:30
parent 7792e5cbda
commit 0eedc67144
1 changed files with 25 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
scrape.py
View File

@ -37,6 +37,16 @@ print('WebDriver initialised')
##### Do stuff ############################################## ##### Do stuff ##############################################
# User class, holds all the data we will be collecting from user pages
# It's being used here as a more structured alternative to a dictionary
class User:
url_username = ''
username = ''
track_count = ''
like_count = ''
following_count = ''
follower_count = ''
user_dict = {} user_dict = {}
users_to_process = ['thomotron', 'lacheque', 'slynk'] users_to_process = ['thomotron', 'lacheque', 'slynk']
@ -45,26 +55,29 @@ for user_str in users_to_process:
if user_str in user_dict.keys(): if user_str in user_dict.keys():
continue continue
# Initialise our user object to store our values in
user = User()
user.url_username = user_str
# Get the user's profile page and soup it
driver.get('https://soundcloud.com/' + user_str) driver.get('https://soundcloud.com/' + user_str)
soup = BeautifulSoup(driver.page_source, 'lxml') soup = BeautifulSoup(driver.page_source, 'lxml')
# Initialise our user object to store our values in # Grab their username
user = {}
# Use stripped_strings generator as workaround for users with premium badge # Use stripped_strings generator as workaround for users with premium badge
username = next(soup.find(class_='profileHeaderInfo__userName').stripped_strings) username = next(soup.find(class_='profileHeaderInfo__userName').stripped_strings)
user['username'] = username user.username = username
print(username)
track_count = int(soup.find('a', href='/' + username.lower() + '/tracks', class_='infoStats__statLink').div.string) # Grab their track count
user['track_count'] = track_count track_count = soup.find('a', href='/' + user.url_username + '/tracks', class_='infoStats__statLink').div.string
print(track_count) user.track_count = track_count
# Grab their like count
like_count = soup.find('a', href='/' + user.url_username + '/likes').find(class_='sidebarHeader__actualTitle').string.split(' ')[0]
user.like_count = like_count
like_count = int(soup.find('a', href='/' + username.lower() + '/likes').find(class_='sidebarHeader__actualTitle').string.split(' ')[0])
user['like_count'] = like_count
print(like_count)
# Finally add the user to the dictionary # Finally add the user to the dictionary
user_dict['user_str'] = user user_dict[user.url_username] = user
driver.quit() driver.quit()