from lxml import html
import requests
import os, sys
# this relies on a chrome plug in: https://chrome.google.com/webstore/detail/downalbum/cgjnhhjpfcdhbhlcmmjppicjmgfkppok
#use the plug-in, it allows you to download an album, along with an .htm file. This script extracts the relevant data from that .htm and outputs an .html set to go on dave's site
# set this to what you want the title of the html page to be, in quotes
pagetitle = "Psychoanalysis and Neuroscience"
# This is the text at the top of the page, eg "From a Columbia-Barnard-Rutgers workshop in the philosophy of mind at the Brooklyn Zen Center in Gowanus, August 2017". In quotes.
pagedescription = "Psychoanalysis and Neuroscience: A Debate \"Is Psychoanalysis Relevant to Neuroscience\", May 3, 2019 followed by a workshop on Consciousness, Memory and the Freudian Unconscious, May 4, 2019, NYU"
# This is the name of the album, eg, "Summer2016", if the pic folder is "Summer2016@@".
albumname = "psychoanalysisneuroscience"
#write in the name of the target downloaded htm file
with open(r'psychoanalysisneuroscience.htm', "r", encoding="latin-1") as f:
page = f.read()
tree = html.fromstring(page)
albumbase = tree.xpath('//div[@rel="gallery"]')
tagsbypic = [tree.xpath('//div[@rel="gallery"]' + '[' + str(n+1) +']' + '//div[@class="tagName"]/span[text()]') for n in range(0,len(albumbase))]
#testalbumsecondelement = tree.xpath('//div[@rel="gallery"]' + '[2]' + '//div[@class="tagName"]/span[text()]')
#still needs text conversion
capsbypic = [tree.xpath('//div[@rel="gallery"]' + '[' + str(n+1) +']' + '//div[@class="caption"]/p[text()]') for n in range(0,len(albumbase))]
idbypic =[tree.xpath('//div[@rel="gallery"]' + '[' + str(n+1) +']' + '//a[@class="fancybox"]/@href') for n in range(0,len(albumbase))]
#picidsproto = [element.text for element in idbypic]
picidproto = [str(element).split("_files/") for element in idbypic]
picid = [f[-1] for f in picidproto]
htmlstring = """
""" + pagetitle + """
""" + pagedescription + """
"""
for n in range(0,len(albumbase)):
picfilename = picid[n].replace("']","")
if len(capsbypic[n]) != 0:
caption = [element.text for element in capsbypic[n]]
if len(tagsbypic[n]) != 0:
tags = [element.text for element in tagsbypic[n]]
dedupedtags = list(dict.fromkeys(tags))
tagstring = ", ".join(dedupedtags)
htmlstring += """
![](\"""")
""" + caption[0] + """
"""
else:
htmlstring += """
""" + caption[0] + """
"""
else:
if len(tagsbypic[n]) != 0:
tags = [element.text for element in tagsbypic[n]]
dedupedtags = list(dict.fromkeys(tags))
tagstring = ", ".join(dedupedtags)
htmlstring += """
""" + tagstring + """
"""
else:
htmlstring += """
"""
htmlstring += """
Go to:
"""
Html_file = open(albumname + ".html","w",encoding='utf8')
Html_file.write(htmlstring)
Html_file.close()
#WORKS! JUST BE SURE TO FIX THE ACCENTS AND FORMATTING ON THE NAMES... MIGHT HAVE TO DO FIND/REPLACE