extract your "Top 100 Songs 2018" (spotify)

gistfile1.txt

"""Prerequisites:
(1) You'll first need to open up the developer console in e.g. Chrome (cmd-shift-c)
(2) Locate the div element with id "main" (should be relatively easy to find as it's the main enclosing div in the body)
(3) Copy all the inner html of that div (easy way- right-click and select "Edit as HTML", then copy normally)
(4) Save that to a file somewhere (e.g. /tmp/tracklist.html)
(5) Open up a python shell (preferably iPython!) and execute the following
"""

import lxml.html

# read in the file from wherever it is saved
with open('/tmp/tracklist.html', 'r') as f:
   html = f.read()   

# convert the html blob into an lxml tree
tree = lxml.html.fragment_fromstring(html)

# grab all the songs
songs = tree.xpath("//div[contains(concat(' ', normalize-space(@class), ' '),' tracklist-name ')]")

# grab all the artist/album info
metadata = tree.xpath("//div[contains(concat(' ', normalize-space(@class), ' '),' second-line ')]")

# zip the songs and metadata together, clean up the results a little, and spit them out
for s, m in zip(songs, metadata):
    meta = m.text_content()[8:] if "Explicit" in m.text_content() else m.text_content()
    meta = meta.replace('•', '/')
    print("%s - %s" % (s.text, meta))