find PMID in txt file, fetch XML from pubmed, parse into jekyll post, write markdown file to ~/Desktop

ifttt_rss2md.py

#!/usr/bin/env python
# encoding: utf-8
"""
ifttt_rss2md.py

Created on 2014-07-14.

The MIT License (MIT)

Copyright (c) 2014. Shawn Douglas

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.

DESCRIPTION:

1. Extracts a PMID from an IFTTT-generated txt file.
2. Fetches XML for PMID and parses into a jekyll blog post.
3. Writes the blog post as markdown to ~/Desktop/ 
4. relocates the IFTTT file to a "Processed" subdirectory.

DEPENDENCIES:

Install https://github.com/martinblech/xmltodict 
$ pip install xmltodict

INSTRUCTIONS:

1. Find an RSS feed url that you want to track.

2. Create IFTTT rule like https://ifttt.com/recipes/191206-pubmed-rss-to-dropbox-txt

Set to place new feed items in "~/Dropbox/IFTTT/Feeds/myfeed"

I created the following directory structure in Dropbox:

IFTTT/
    Feeds/
        myfeed/
    Processed/
        myfeed/
    scripts/
        ifttt_rs2md.py (this file)

3. Create an Automator "Folder Action" workflow that receives files
and folders added to "~/Dropbox/IFTTT/Feeds/myfeed" and "Runs Shell Script" with 

Shell: /bin/bash 
Pass input: as arguments

for f in "$@"
do
	python ~/Dropbox/IFTTT/scripts/ifttt_rss2md.py "$f"
done

"""

import re
import sys
import urllib2
import xmltodict
import json
import shutil
from os.path import expanduser
from xattr import xattr
from struct import unpack

pmid_re = "PMID: ([0-9]+)"


post_template = """---
layout: post
published: true
title: "%s"
date: %s 12:00:00
pmid: %s
authors: "%s"
firstauthor: "%s"
journalname: "%s"
journalvolume: %s
journalissue: %s
journalpages: %s
---

%s

"""

def main(argv=None):
    if argv is None:
        argv = sys.argv

    pmidString = None

    with open(argv[1], 'r') as f:
        read_data = f.read()
        pmidObj = re.search(pmid_re, read_data)
        if pmidObj:
            pmidString = pmidObj.group(1)

    if pmidString:
        pubmid_url = "http://www.ncbi.nlm.nih.gov/pubmed/%s?report=xml&format=text" % pmidString
        response = urllib2.urlopen(pubmid_url)
        html = response.read()
        html = html.replace("&lt;", "<").replace("&gt;", ">")
        d = xmltodict.parse(html)
        article = d["pre"]["PubmedArticle"]
        citation = article["MedlineCitation"]
        pmid = citation["PMID"]["#text"]
        date = citation["DateCreated"]
        dateStr = "%s-%s-%s" % (date["Year"], date["Month"], date["Day"])

        journal = citation["Article"]["Journal"]
        journalname = journal["ISOAbbreviation"]
        journalvolume = ""
        journalissue = ""
        journalpages = ""
        pubdate = journal["JournalIssue"]["PubDate"]

        if "Month" in pubdate and "Day" in pubdate:
            pubdateStr = "%s %s %s" % (pubdate["Year"], pubdate["Month"], pubdate["Day"])
        else:
            pubdateStr = pubdate["Year"]

        ji = journal["JournalIssue"]
        vipStr = ""
        if "Volume" in ji and "Issue" in ji:
            vipStr = "<b>%s</b>(%s)" % (ji["Volume"], ji["Issue"])
            journalvolume = ji["Volume"]
            journalissue = ji["Issue"]
            if "Pagination" in citation["Article"]:
                vipStr += ":%s" % citation["Article"]["Pagination"]["MedlinePgn"]
                journalpages = citation["Article"]["Pagination"]["MedlinePgn"]
            citeStr = "*%s %s;%s*" % (journalname, pubdateStr, vipStr)
        else:
            citeStr = "*%s %s*" % (journalname, pubdateStr)
        title = citation["Article"]["ArticleTitle"].replace('"', "'")
        # print title
        abstract = citation["Article"]["Abstract"]["AbstractText"]
        authorCount = len(citation["Article"]["AuthorList"]["Author"])
        authors = citation["Article"]["AuthorList"]["Author"]
        if type(authors) is dict:
            authors = [authors]
        authorList = []
        for author in authors:
            authorList.append("%s %s" % (author["LastName"], author["Initials"]))
        authorStr = ", ".join(authorList)
        firstAuthorLN = authors[0]["LastName"]

        # Write the markdown file in ~/Desktop/
        mdFilename = "%s-%s.md" % (dateStr, firstAuthorLN.lower())
        mdContent = post_template % (title, dateStr, pmid, authorStr, authorList[0], journalname, journalvolume, journalissue, journalpages, abstract)
        mdContent = mdContent.encode("utf-8")
        # print mdFilename
        # print mdContent
        home = expanduser("~")
        f = open(home+"/Desktop/"+mdFilename, 'w')
        f.write(mdContent)
        f.close()

        # label the new file red for increased visiblity
        # from https://github.com/danthedeckie/finder_colors
        color = 'green'
        COLORS = {'none': 0, 'gray': 2, 'green': 4, 'purple': 6, 
                  'blue': 8, 'yellow': 10, 'red': 12, 'orange': 14}
        _FINDER_INFO_TAG = u'com.apple.FinderInfo'
        BLANK = 32*chr(0)
        attrs = xattr(home+"/Desktop/"+mdFilename)
        if _FINDER_INFO_TAG in attrs:
            previous = attrs[_FINDER_INFO_TAG]
        else:
            previous = BLANK
        prev_color_extra_bits = ord(previous[9]) & (255-14)

        # these are all the bits in previous[9] not used for color.
        new = previous[:9] \
            + chr(COLORS[color] \
            + prev_color_extra_bits) \
            + previous[10:]
        attrs.set(_FINDER_INFO_TAG, new)

        # Clean up - move the file to "Processed directory"
        # something like ['','Users', 'shawn', 'Dropbox', 'IFTTT', 'Feeds', 'cmp', 'file..txt']
        src = argv[1].split("/")
        # something like ['','Users', 'shawn', 'Dropbox', 'IFTTT', 'Processed', 'cmp', 'file..txt']
        dest = "/".join(src[:-3] + ["Processed"] + src[-2:])
        shutil.move(argv[1],dest)


if __name__ == "__main__":
    sys.exit(main())