samuelkordik · February 16, 2023 07:23
diff --git a/readinglist_pinboard.py b/readinglist_pinboard.py
 #!/Users/samuelkordik/.pyenv/shims/python
 # ReadingListCatcher
 # - A script for exporting Safari Reading List items to Markdown and Pinboard
 # Originally by Brett Terpstra 2015, <https://brettterpstra.com/2015/01/06/reading-list-catcher/>
 # Modifications by Zach Fine made in 2020 to use the original reading list item in the
 #   posts to pinboard.
 # Updated 2021-06-21 by Samuel Kordik to fix errors due to deprecated API in plistlib,
 #   changes to Pinboard api and Pinboard python lib; added enhanced logging output
 #   and error handling to work as a cron job or shell script.
 # Uses code from <https://gist.github.com/robmathers/5995026>
 # Requires Python pinboard lib for Pinboard.in import:
 #     `easy_install pinboard` or `pip install pinboard`

 import plistlib
 from shutil import copy
 import subprocess
 import os
 from tempfile import gettempdir
 import sys
 import atexit
 import re
 import time
 from datetime import date, datetime, timedelta
 from os import path
 import pytz

 DEFAULT_EXPORT_TYPE = 'all' # pb, md or all
 from secrets import PINBOARD_API_KEY # This relies on setting this value in a separate file 'secrets.py'
 #PINBOARD_API_KEY = 'Username:XXXXXXXXXXXXXXXXXXXX' # https://pinboard.in/settings/password
 BOOKMARKS_MARKDOWN_FILE = '~/Documents/Reading List Bookmarks.markdown' # Markdown file if using md export
 BOOKMARKS_PLIST = '~/Library/Safari/Bookmarks.plist' # Shouldn't need to modify

 bookmarksFile = os.path.expanduser(BOOKMARKS_PLIST)
 markdownFile = os.path.expanduser(BOOKMARKS_MARKDOWN_FILE)

 # Make a copy of the bookmarks plist. No need for conversion.
 tempDirectory = gettempdir()
 bookmarksFileCopy = copy(bookmarksFile, tempDirectory)

 def removeTempFile():
    try:
        os.remove(bookmarksFileCopy)
    except FileNotFoundError as e:
        pass    # For some reason, when run as a cron job this always comes up as an error.
    except:
        e = sys.exc_info()
        sys.stdout.write("Error: %s" % e)
        raise

 atexit.register(removeTempFile) # Delete the temp file when the script finishes

 class _readingList():
    def __init__(self, exportType):
       
        self.postedCount = 0
        self.exportType = exportType
        
        timestamp = datetime.now().strftime("%Y-%m-%dT%H:%M:%S")

        if self.exportType == 'pb':
            print("%s: Exporting bookmarks to Pinboard" % timestamp)
        elif self.exportType == 'md':
            print("%s: Exporting bookmarks to Markdown file %s" % (timestamp, BOOKMARKS_MARKDOWN_FILE))
        else:
            print("%s: Exporting bookmarks with exportType %s" % (timestamp, self.exportType))

        if self.exportType == 'pb':
            import pinboard
            self.pb = pinboard.Pinboard(PINBOARD_API_KEY)

        with open(bookmarksFileCopy, 'rb') as fp:
            plist = plistlib.load(fp)
            

         # There should only be one Reading List item, so take the first one
        readingList = [item for item in plist['Children'] if 'Title' in item and item['Title'] == 'com.apple.ReadingList'][0]

        # Determine last synced bookmark
        if self.exportType == 'pb':
            # For Pinboard, use the last synced bookmark OR start from 2013-01-01 if no synced bookmarks
            lastRLBookmark = self.pb.posts.recent(tag='.readinglist', count=1)
            if len(lastRLBookmark['posts']) > 0:
                last = lastRLBookmark['date']
            else:
                last = datetime.strptime("2013-01-01 00:00:00 UTC", '%Y-%m-%d %H:%M:%S UTC')
        else:            
            # For Markdown, get the markdown file (if it exists) and pull the updated time from the header of that file
            # Fall back to 2013-01-01 if not found.
            self.content = ''
            self.newcontent = ''
            # last = time.strptime((datetime.now() - timedelta(days = 1)).strftime('%c'))
            last = time.strptime("2013-01-01 00:00:00 UTC", '%Y-%m-%d %H:%M:%S UTC')

            if not os.path.exists(markdownFile):
                open(markdownFile, 'a').close()
            else:
                with open (markdownFile, 'r') as mdInput:
                    self.content = mdInput.read()
                    matchLast = re.search(re.compile('(?m)^Updated: (\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2} UTC)'), self.content)
                    if matchLast != None:
                        last = time.strptime(matchLast.group(1), '%Y-%m-%d %H:%M:%S UTC')

            last = datetime(*last[:6])

            rx = re.compile("(?m)^Updated: (\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}) UTC")
            self.content = re.sub(rx,'',self.content).strip()

        # Process new bookmarks in Reading List
        if 'Children' in readingList:
            cleanRx = re.compile("[\|\`\:_\*\n]")
            for item in readingList['Children']:
                if item['ReadingList']['DateAdded'] > last:
                    addtime = pytz.utc.localize(item['ReadingList']['DateAdded']).strftime('%c')
                    #print(item['URIDictionary']['title'])
                    title = re.sub(cleanRx, ' ', item['URIDictionary']['title'])
                    title = re.sub(' +', ' ', title)
                    url = item['URLString']
                    description = ''

                    if 'PreviewText' in item['ReadingList']:
                        description = item['ReadingList']['PreviewText']
                        description = re.sub(cleanRx, ' ', description)
                        description = re.sub(' +', ' ', description)

                    if self.exportType == 'md':
                        self.itemToMarkdown(addtime, title, url, description)
                    else:
                        if not title.strip():
                            title = 'no title'
                        post_time=pytz.utc.localize(item['ReadingList']['DateAdded'])
                        self.itemToPinboard(post_time, title, url, description)
                else:
                    break

        # Write output logging information                    
        pluralized = 'bookmarks' if self.postedCount > 1 else 'bookmark'
        
        if self.exportType == 'pb':
            if self.postedCount > 0:
                sys.stdout.write('Added ' + str(self.postedCount) + ' new ' + pluralized + ' to Pinboard')
            else:
                sys.stdout.write('No new bookmarks found in Reading List')
        else:
            mdHandle = open(markdownFile, 'w')
            mdHandle.write('Updated: ' + datetime.utcnow().strftime('%Y-%m-%d %H:%M:%S') + " UTC\n\n")
            mdHandle.write(self.newcontent + self.content)
            mdHandle.close()
            if self.postedCount > 0:
                sys.stdout.write('Added ' + str(self.postedCount) + ' new ' + pluralized + ' to ' + markdownFile)
            else:
                sys.stdout.write('No new bookmarks found in Reading List')

        sys.stdout.write("\n")

    def itemToMarkdown(self, addtime, title, url, description):
        self.newcontent += '- [' + title + '](' + url + ' "Added on ' + addtime + '")'
        if not description == '':
            self.newcontent += "\n\n    > " + description
        self.newcontent += "\n\n"
        self.postedCount += 1

    def itemToPinboard(self, post_time, title, url, description):
        try:
            suggestions = self.pb.posts.suggest(url=url)
            tags = suggestions[0]['popular']
            tags.append('.readinglist')

            pinboard_add_status = self.pb.posts.add(url=url, description=title, \
                extended=description, tags=tags, shared=False, \
                toread=True)

            # Error checking for pinboard api
            assert(pinboard_add_status), "Failed to save %s" %title

            sys.stdout.write("Added %s to Pinboard: %s\n" % (title, pinboard_add_status))

            self.postedCount += 1
        except:
            e = sys.exc_info()
            sys.stdout.write("Error: %s" % e)
            raise
        

 if __name__ == "__main__":
    
    exportTypes = []
    
    if len(sys.argv) > 1: # Additional arguments provided
        for arg in sys.argv:
            if re.match("^(md|pb|all)$",arg) and exportTypes.count(arg) == 0:
                exportTypes.append(arg)
    else:
        exportTypes.append(DEFAULT_EXPORT_TYPE)
    
    for eType in exportTypes:
        if eType == 'all':
            _readingList('pb')
            _readingList('md')
        else:
            _readingList(eType)
	#!/Users/samuelkordik/.pyenv/shims/python
	# ReadingListCatcher
	# - A script for exporting Safari Reading List items to Markdown and Pinboard
	# Originally by Brett Terpstra 2015, <https://brettterpstra.com/2015/01/06/reading-list-catcher/>
	# Modifications by Zach Fine made in 2020 to use the original reading list item in the
	# posts to pinboard.
	# Updated 2021-06-21 by Samuel Kordik to fix errors due to deprecated API in plistlib,
	# changes to Pinboard api and Pinboard python lib; added enhanced logging output
	# and error handling to work as a cron job or shell script.
	# Uses code from <https://gist.github.com/robmathers/5995026>
	# Requires Python pinboard lib for Pinboard.in import:
	# `easy_install pinboard` or `pip install pinboard`

	import plistlib
	from shutil import copy
	import subprocess
	import os
	from tempfile import gettempdir
	import sys
	import atexit
	import re
	import time
	from datetime import date, datetime, timedelta
	from os import path
	import pytz

	DEFAULT_EXPORT_TYPE = 'all' # pb, md or all
	from secrets import PINBOARD_API_KEY # This relies on setting this value in a separate file 'secrets.py'
	#PINBOARD_API_KEY = 'Username:XXXXXXXXXXXXXXXXXXXX' # https://pinboard.in/settings/password
	BOOKMARKS_MARKDOWN_FILE = '~/Documents/Reading List Bookmarks.markdown' # Markdown file if using md export
	BOOKMARKS_PLIST = '~/Library/Safari/Bookmarks.plist' # Shouldn't need to modify

	bookmarksFile = os.path.expanduser(BOOKMARKS_PLIST)
	markdownFile = os.path.expanduser(BOOKMARKS_MARKDOWN_FILE)

	# Make a copy of the bookmarks plist. No need for conversion.
	tempDirectory = gettempdir()
	bookmarksFileCopy = copy(bookmarksFile, tempDirectory)

	def removeTempFile():
	try:
	os.remove(bookmarksFileCopy)
	except FileNotFoundError as e:
	pass # For some reason, when run as a cron job this always comes up as an error.
	except:
	e = sys.exc_info()
	sys.stdout.write("Error: %s" % e)
	raise

	atexit.register(removeTempFile) # Delete the temp file when the script finishes

	class _readingList():
	def __init__(self, exportType):

	self.postedCount = 0
	self.exportType = exportType

	timestamp = datetime.now().strftime("%Y-%m-%dT%H:%M:%S")

	if self.exportType == 'pb':
	print("%s: Exporting bookmarks to Pinboard" % timestamp)
	elif self.exportType == 'md':
	print("%s: Exporting bookmarks to Markdown file %s" % (timestamp, BOOKMARKS_MARKDOWN_FILE))
	else:
	print("%s: Exporting bookmarks with exportType %s" % (timestamp, self.exportType))

	if self.exportType == 'pb':
	import pinboard
	self.pb = pinboard.Pinboard(PINBOARD_API_KEY)

	with open(bookmarksFileCopy, 'rb') as fp:
	plist = plistlib.load(fp)


	# There should only be one Reading List item, so take the first one
	readingList = [item for item in plist['Children'] if 'Title' in item and item['Title'] == 'com.apple.ReadingList'][0]

	# Determine last synced bookmark
	if self.exportType == 'pb':
	# For Pinboard, use the last synced bookmark OR start from 2013-01-01 if no synced bookmarks
	lastRLBookmark = self.pb.posts.recent(tag='.readinglist', count=1)
	if len(lastRLBookmark['posts']) > 0:
	last = lastRLBookmark['date']
	else:
	last = datetime.strptime("2013-01-01 00:00:00 UTC", '%Y-%m-%d %H:%M:%S UTC')
	else:
	# For Markdown, get the markdown file (if it exists) and pull the updated time from the header of that file
	# Fall back to 2013-01-01 if not found.
	self.content = ''
	self.newcontent = ''
	# last = time.strptime((datetime.now() - timedelta(days = 1)).strftime('%c'))
	last = time.strptime("2013-01-01 00:00:00 UTC", '%Y-%m-%d %H:%M:%S UTC')

	if not os.path.exists(markdownFile):
	open(markdownFile, 'a').close()
	else:
	with open (markdownFile, 'r') as mdInput:
	self.content = mdInput.read()
	matchLast = re.search(re.compile('(?m)^Updated: (\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2} UTC)'), self.content)
	if matchLast != None:
	last = time.strptime(matchLast.group(1), '%Y-%m-%d %H:%M:%S UTC')

	last = datetime(*last[:6])

	rx = re.compile("(?m)^Updated: (\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}) UTC")
	self.content = re.sub(rx,'',self.content).strip()

	# Process new bookmarks in Reading List
	if 'Children' in readingList:
	cleanRx = re.compile("[\\|\`\:_\*\n]")
	for item in readingList['Children']:
	if item['ReadingList']['DateAdded'] > last:
	addtime = pytz.utc.localize(item['ReadingList']['DateAdded']).strftime('%c')
	#print(item['URIDictionary']['title'])
	title = re.sub(cleanRx, ' ', item['URIDictionary']['title'])
	title = re.sub(' +', ' ', title)
	url = item['URLString']
	description = ''

	if 'PreviewText' in item['ReadingList']:
	description = item['ReadingList']['PreviewText']
	description = re.sub(cleanRx, ' ', description)
	description = re.sub(' +', ' ', description)

	if self.exportType == 'md':
	self.itemToMarkdown(addtime, title, url, description)
	else:
	if not title.strip():
	title = 'no title'
	post_time=pytz.utc.localize(item['ReadingList']['DateAdded'])
	self.itemToPinboard(post_time, title, url, description)
	else:
	break

	# Write output logging information
	pluralized = 'bookmarks' if self.postedCount > 1 else 'bookmark'

	if self.exportType == 'pb':
	if self.postedCount > 0:
	sys.stdout.write('Added ' + str(self.postedCount) + ' new ' + pluralized + ' to Pinboard')
	else:
	sys.stdout.write('No new bookmarks found in Reading List')
	else:
	mdHandle = open(markdownFile, 'w')
	mdHandle.write('Updated: ' + datetime.utcnow().strftime('%Y-%m-%d %H:%M:%S') + " UTC\n\n")
	mdHandle.write(self.newcontent + self.content)
	mdHandle.close()
	if self.postedCount > 0:
	sys.stdout.write('Added ' + str(self.postedCount) + ' new ' + pluralized + ' to ' + markdownFile)
	else:
	sys.stdout.write('No new bookmarks found in Reading List')

	sys.stdout.write("\n")

	def itemToMarkdown(self, addtime, title, url, description):
	self.newcontent += '- [' + title + '](' + url + ' "Added on ' + addtime + '")'
	if not description == '':
	self.newcontent += "\n\n > " + description
	self.newcontent += "\n\n"
	self.postedCount += 1

	def itemToPinboard(self, post_time, title, url, description):
	try:
	suggestions = self.pb.posts.suggest(url=url)
	tags = suggestions[0]['popular']
	tags.append('.readinglist')

	pinboard_add_status = self.pb.posts.add(url=url, description=title, \
	extended=description, tags=tags, shared=False, \
	toread=True)

	# Error checking for pinboard api
	assert(pinboard_add_status), "Failed to save %s" %title

	sys.stdout.write("Added %s to Pinboard: %s\n" % (title, pinboard_add_status))

	self.postedCount += 1
	except:
	e = sys.exc_info()
	sys.stdout.write("Error: %s" % e)
	raise


	if __name__ == "__main__":

	exportTypes = []

	if len(sys.argv) > 1: # Additional arguments provided
	for arg in sys.argv:
	if re.match("^(md\|pb\|all)$",arg) and exportTypes.count(arg) == 0:
	exportTypes.append(arg)
	else:
	exportTypes.append(DEFAULT_EXPORT_TYPE)

	for eType in exportTypes:
	if eType == 'all':
	_readingList('pb')
	_readingList('md')
	else:
	_readingList(eType)