Develop Reference

ValueError: stat: path too long for Windows on Jupyter Notebook parsing a URL request

I am trying to parse my company Odata data to construct a proportion of late suppliers taking the CompanyName and LateDays fields.
I opened the file and converted it into a string since I found a really helpful post on how request urls with authentication, and I obtained my string text containing the whole report. The report is written in ?XML and I am using Python 3.7 in Jupyter Notebook to handle it.
I found another post that queries a XML file similar to mine using a class method, but my output is the error ValueError: stat: path too long for Windows.
How can I fix this?
Thanks!
import requests
import pandas as pd
import numpy as np
import base64
import urllib.request
request = urllib.request.Request('https://myUrl_OData')
base64string = base64.b64encode(bytes('%s:%s' % ('Myusername', 'Mypassword'),'ascii'))
request.add_header("Authorization", "Basic %s" % base64string.decode('utf-8'))
result = urllib.request.urlopen(request)
resulttext = result.read()
text = resulttext.decode(encoding='utf-8',errors='ignore')
from xml.sax import parse
from xml.sax.handler import ContentHandler
class properties(ContentHandler):
def __init__(self):
self.elements = [] # stack of elements
self.char_data = u'' # string buffer
self.current_vendor = u''
self.current_latedays = u''
def startElement(self, name, attrs):
if companyname == u'CompanyName':
self.elements.append(u'CompanyName')
if latedays == u'LateDays':
self.elements.append(u'LateDays')
def characters(self, chars):
if len(self.elements) > 0 and self.elements[-1] in [u'CompanyName', u'LateDays']:
self.char_data += chars
def endElement(self, name):
self.elements.pop() if len(self.elements) > 0 else None
if companyname == u'CompanyName':
self.current_vendor = self.char_data
self.char_data = ''
if latedays == u'LateDays':
self.current_latedays = self.char_data
self.char_data = ''
if companyname == 'CompanyName':
if self.current_latedays == u'LateDays':
print('Found:', self.current_customer)
# clear the buffers now that is finished
self.current_year = u''
self.current_customer = u''
self.char_data = u''
parse(r"\\\\?\\" + text, properties())

Your error doesn't seem to be related with XML parsing but with your OS limitations.
On a Windows-based OS, the path of a file cannot be longer than ~260 characters (ref).
Try to reduce the length of your filename, or reduce the number of nested folders leading to your data.

Python script - Blogger2Wordpress - how to save file?

I use the blogger2wordpress python script that Google released back in 2010 (https://code.google.com/archive/p/google-blog-converters-appengine/downloads), to convert a 95mb blogger export file to wordpress wxr format.
However, the script has this code:
#!/usr/bin/env python
# Copyright 2008 Google Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0.txt
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os.path
import logging
import re
import sys
import time
from xml.sax.saxutils import unescape
import BeautifulSoup
import gdata
from gdata import atom
import iso8601
import wordpress
__author__ = 'JJ Lueck (EMAIL#gmail.com)'
###########################
# Constants
###########################
BLOGGER_URL = 'http://www.blogger.com/'
BLOGGER_NS = 'http://www.blogger.com/atom/ns#'
KIND_SCHEME = 'http://schemas.google.com/g/2005#kind'
YOUTUBE_RE = re.compile('http://www.youtube.com/v/([^&]+)&?.*')
YOUTUBE_FMT = r'[youtube=http://www.youtube.com/watch?v=\1]'
GOOGLEVIDEO_RE = re.compile('(http://video.google.com/googleplayer.swf.*)')
GOOGLEVIDEO_FMT = r'[googlevideo=\1]'
DAILYMOTION_RE = re.compile('http://www.dailymotion.com/swf/(.*)')
DAILYMOTION_FMT = r'[dailymotion id=\1]'
###########################
# Translation class
###########################
class Blogger2Wordpress(object):
"""Performs the translation of a Blogger export document to WordPress WXR."""
def __init__(self, doc):
"""Constructs a translator for a Blogger export file.
Args:
doc: The WXR file as a string
"""
# Ensure UTF8 chars get through correctly by ensuring we have a
# compliant UTF8 input doc.
self.doc = doc.decode('utf-8', 'replace').encode('utf-8')
# Read the incoming document as a GData Atom feed.
self.feed = atom.FeedFromString(self.doc)
self.next_id = 1
def Translate(self):
"""Performs the actual translation to WordPress WXR export format.
Returns:
A WordPress WXR export document as a string, or None on error.
"""
# Create the top-level document and the channel associated with it.
channel = wordpress.Channel(
title = self.feed.title.text,
link = self.feed.GetAlternateLink().href,
base_blog_url = self.feed.GetAlternateLink().href,
pubDate = self._ConvertPubDate(self.feed.updated.text))
posts_map = {}
for entry in self.feed.entry:
# Grab the information about the entry kind
entry_kind = ""
for category in entry.category:
if category.scheme == KIND_SCHEME:
entry_kind = category.term
if entry_kind.endswith("#comment"):
# This entry will be a comment, grab the post that it goes to
in_reply_to = entry.FindExtensions('in-reply-to')
post_item = None
# Check to see that the comment has a corresponding post entry
if in_reply_to:
post_id = self._ParsePostId(in_reply_to[0].attributes['ref'])
post_item = posts_map.get(post_id, None)
# Found the post for the comment, add the commment to it
if post_item:
# The author email may not be included in the file
author_email = ''
if entry.author[0].email:
author_email = entry.author[0].email.text
# Same for the the author's url
author_url = ''
if entry.author[0].uri:
author_url = entry.author[0].uri.text
post_item.comments.append(wordpress.Comment(
comment_id = self._GetNextId(),
author = entry.author[0].name.text,
author_email = author_email,
author_url = author_url,
date = self._ConvertDate(entry.published.text),
content = self._ConvertContent(entry.content.text)))
elif entry_kind.endswith('#post'):
# This entry will be a post
post_item = self._ConvertEntry(entry, False)
posts_map[self._ParsePostId(entry.id.text)] = post_item
channel.items.append(post_item)
elif entry_kind.endswith('#page'):
# This entry will be a static page
page_item = self._ConvertEntry(entry, True)
posts_map[self._ParsePageId(entry.id.text)] = page_item
channel.items.append(page_item)
wxr = wordpress.WordPressWxr(channel=channel)
return wxr.WriteXml()
def _ConvertEntry(self, entry, is_page):
"""Converts the contents of an Atom entry into a WXR post Item element."""
# A post may have an empty title, in which case the text element is None.
title = ''
if entry.title.text:
title = entry.title.text
# Check here to see if the entry points to a draft or regular post
status = 'publish'
if entry.control and entry.control.draft:
status = 'draft'
# If no link is present in the Blogger entry, just link
if entry.GetAlternateLink():
link = entry.GetAlternateLink().href
else:
link = BLOGGER_URL
# Declare whether this is a post of a page
post_type = 'post'
if is_page:
post_type = 'page'
blogger_blog = ''
blogger_permalink = ''
if entry.GetAlternateLink():
blogger_path_full = entry.GetAlternateLink().href.replace('http://', '')
blogger_blog = blogger_path_full.split('/')[0]
blogger_permalink = blogger_path_full[len(blogger_blog):]
# Create the actual item element
post_item = wordpress.Item(
title = title,
link = link,
pubDate = self._ConvertPubDate(entry.published.text),
creator = entry.author[0].name.text,
content = self._ConvertContent(entry.content.text),
post_id = self._GetNextId(),
post_date = self._ConvertDate(entry.published.text),
status = status,
post_type = post_type,
blogger_blog = blogger_blog,
blogger_permalink = blogger_permalink,
blogger_author = entry.author[0].name.text)
# Convert the categories which specify labels into wordpress labels
for category in entry.category:
if category.scheme == BLOGGER_NS:
post_item.labels.append(category.term)
return post_item
def _ConvertContent(self, text):
"""Unescapes the post/comment text body and replaces video content.
All <object> and <embed> tags in the post that relate to video must be
changed into the WordPress tags for embedding video,
e.g. [youtube=http://www.youtube.com/...]
If no text is provided, the empty string is returned.
"""
if not text:
return ''
# First unescape all XML tags as they'll be escaped by the XML emitter
content = unescape(text)
# Use an HTML parser on the body to look for video content
content_tree = BeautifulSoup.BeautifulSoup(content)
# Find the object tag
objs = content_tree.findAll('object')
for obj_tag in objs:
# Find the param tag within which contains the URL to the movie
param_tag = obj_tag.find('param', { 'name': 'movie' })
if not param_tag:
continue
# Get the video URL
video = param_tag.attrMap.get('value', None)
if not video:
continue
# Convert the video URL if necessary
video = YOUTUBE_RE.subn(YOUTUBE_FMT, video)[0]
video = GOOGLEVIDEO_RE.subn(GOOGLEVIDEO_FMT, video)[0]
video = DAILYMOTION_RE.subn(DAILYMOTION_FMT, video)[0]
# Replace the portion of the contents with the video
obj_tag.replaceWith(video)
return str(content_tree)
def _ConvertPubDate(self, date):
"""Translates to a pubDate element's time/date format."""
date_tuple = iso8601.parse_date(date)
return date_tuple.strftime('%a, %d %b %Y %H:%M:%S %z')
def _ConvertDate(self, date):
"""Translates to a wordpress date element's time/date format."""
date_tuple = iso8601.parse_date(date)
return date_tuple.strftime('%Y-%m-%d %H:%M:%S')
def _GetNextId(self):
"""Returns the next identifier to use in the export document as a string."""
next_id = self.next_id;
self.next_id += 1
return str(next_id)
def _ParsePostId(self, text):
"""Extracts the post identifier from a Blogger entry ID."""
matcher = re.compile('post-(\d+)')
matches = matcher.search(text)
return matches.group(1)
def _ParsePageId(self, text):
"""Extracts the page identifier from a Blogger entry ID."""
matcher = re.compile('page-(\d+)')
matches = matcher.search(text)
return matches.group(1)
if __name__ == '__main__':
if len(sys.argv) <= 1:
print 'Usage: %s <blogger_export_file>' % os.path.basename(sys.argv[0])
print
print ' Outputs the converted WordPress export file to standard out.'
sys.exit(-1)
wp_xml_file = open(sys.argv[1])
wp_xml_doc = wp_xml_file.read()
translator = Blogger2Wordpress(wp_xml_doc)
print translator.Translate()
wp_xml_file.close()
This scripts outputs the wxr file in the terminal window which is useless for me when the import file has tons of entries.
As I am not familiar with python, how can I modify the script to output the data into a .xml file?
Edit:
I did changed the end of the script to:
wp_xml_file = open(sys.argv[1])
wp_xml_doc = wp_xml_file.read()
translator = Blogger2Wordpress(wp_xml_doc)
print translator.Translate()
fh = open("testoutput.xml", "w")
fh.write(wp_xml_doc);
fh.close();
wp_xml_file.close()
But the produced file is an "invalid wxr file" :/
Can anybody help? Thanks!

Quick and dirty answer:
Output to the stdout is normal behaviour.
You might want to redirect it to a file for instance:
python2 blogger2wordpress your_blogger_export_file > backup
The output will be saved in the file named backup.
Or you can replace print translator.Translate() by
with open('output_file', 'w') as fd:
fd.write(translator.Translate())
This should do the trick (haven't tried).

Parsing a (modified) RIS file with Python

I have a bunch of (modified) RIS files. The toy example looks like the following:
Record #1 of 2
ID: CN-01160769
AU: Uedo N
AU: Kasiser R
TI: Development of an E-learning system
SO: United European Gastroenterology Journal
YR: 2015
Record #2 of 2
ID: CN-01070265
AU: Krogh LQ
TI: E-learning in pediatric basic life support
SO: Resuscitation
YR: 2015
In brief, each record starts with Record # line and ends with two blank lines. The task is to parse the file and extract tags and fields.
Pasted below is my current code (adapted from here):
import re
class RIS:
""" RIS file structure """
def __init__(self, in_file=None):
""" Initialize and parse input """
self.records = []
if in_file:
self.parse(in_file)
def parse(self, in_file):
""" Parse input file """
self.current_tag = None
self.current_record = None
prog = re.compile("^([A-Z][A-Z0-9]): (.*)")
lines = []
# Eliminate blank lines
for line in in_file:
line = line.strip()
if len(line) > 0:
lines.append(line)
for line in lines:
match = prog.match(line)
if match:
tag = match.groups()[0]
field = match.groups()[1]
self.process_field(tag, field)
else:
raise ValueError(line)
def process_field(self, tag, field):
""" Process RIS file field """
if tag == "ID":
self.current_record = {tag: field}
elif tag == "YR":
self.records.append(self.current_record)
self.current_record = None
elif tag in ["AU", "AD"]:
if tag in self.current_record:
self.current_record[tag].append(field)
else:
self.current_record[tag] = [field]
else:
if not tag in self.current_record:
self.current_record[tag] = field
else:
error_str = "Duplicate tag: %s" % tag
raise ValueError(error_str)
def main():
""" Test the code """
import pprint
with open("test.ris", "rt") as ris_file:
ris = RIS(ris_file)
pp = pprint.PrettyPrinter()
pp.pprint(ris.records)
if __name__ == "__main__":
main()
The current code doesn't work, because it doesn't recognize the start tag (e.g., Record 1 of 2) and in addition it doesn't know where the record stops. In the current version of the code I add ID as a start tag and YR as stop tag. However, the code exit with the error:
ValueError: Record #1 of 2
Any suggestions how to properly adapt the code are greatly welcome.

you just need add a judge and break the Record #x of 2 line.
import re
class RIS:
""" RIS file structure """
def __init__(self, in_file=None):
""" Initialize and parse input """
self.records = []
if in_file:
self.parse(in_file)
def parse(self, in_file):
""" Parse input file """
self.current_tag = None
self.current_record = None
prog = re.compile("^([A-Z][A-Z0-9]): (.*)")
lines = []
# Eliminate blank lines
for line in in_file:
line = line.strip()
if len(line) > 0:
lines.append(line)
for line in lines:
if "#" in line:
continue
match = prog.match(line)
if match:
tag = match.groups()[0]
field = match.groups()[1]
self.process_field(tag, field)
else:
raise ValueError(line)
def process_field(self, tag, field):
""" Process RIS file field """
if tag == "ID":
self.current_record = {tag: field}
elif tag == "YR":
self.records.append(self.current_record)
self.current_record = None
elif tag in ["AU", "AD"]:
if tag in self.current_record:
self.current_record[tag].append(field)
else:
self.current_record[tag] = [field]
else:
if not tag in self.current_record:
self.current_record[tag] = field
else:
error_str = "Duplicate tag: %s" % tag
raise ValueError(error_str)
def main():
""" Test the code """
import pprint
with open("test.ris", "rt") as ris_file:
ris = RIS(ris_file)
pp = pprint.PrettyPrinter()
pp.pprint(ris.records)
if __name__ == "__main__":
main()
the add code:
if "#" in line:
continue
the output is
[{'AU': ['Uedo N', 'Kasiser R'],
'ID': 'CN-01160769',
'SO': 'United European Gastroenterology Journal',
'TI': 'Development of an E-learning system'},
{'AU': ['Krogh LQ'],
'ID': 'CN-01070265',
'SO': 'Resuscitation',
'TI': 'E-learning in pediatric basic life support'}]

Cherrypy and Parsing XML Data from multiple files

So this is sort of a piggy-back post of another question I had. I've successfully pulled data from multiple xml files and am able to get the data to display within the terminal using the print function, but when I try to use the return function to show the data in the browser, I only get the data from the first file. Any ideas on why I only get data from the first file rather than all of them? Thanks!
from xml.dom.minidom import parse, parseString
import os, glob, re
import cherrypy
class Root(object):
def index(self):
path = 'C:\Vestigo\XML'
TOTALXML = len(glob.glob(os.path.join(path, '*.xml')))
print TOTALXML
i = 0
for XMLFile in glob.glob(os.path.join(path, '*.xml')):
xmldoc = parse(XMLFile)
order_number = xmldoc.getElementsByTagName('Extrinsic')[0].firstChild.data
order_name = xmldoc.getElementsByTagName('DeliverTo')[0].firstChild.data
street1 = xmldoc.getElementsByTagName('Street1')[0].firstChild.data
state = xmldoc.getElementsByTagName('State')[0].firstChild.data
zip_code = xmldoc.getElementsByTagName('PostalCode')[0].firstChild.data
OUTPUTi = order_number+' '+order_name+' '+street1+' '+state+' '+zip_code
i += 1
print OUTPUTi
return (OUTPUTi, """<br><br>Quit""")
index.exposed = True
def exit(self):
raise SystemExit(0)
exit.exposed = True
def start():
import webbrowser
cherrypy.tree.mount(Root(), '/')
cherrypy.engine.start_with_callback(
webbrowser.open,
('http://localhost:8080/',),
)
cherrypy.engine.block()
if __name__=='__main__':
start()

You are not collecting the data anywhere; you store everything in a variable named OUTPUTi, then only return the last iteration of that variable. Python does not magically make that variable use the i counter.
Use a list to collect the strings:
TOTALXML = len(glob.glob(os.path.join(path, '*.xml')))
print TOTALXML
OUTPUT = []
for XMLFile in glob.glob(os.path.join(path, '*.xml')):
xmldoc = parse(XMLFile)
order_number = xmldoc.getElementsByTagName('Extrinsic')[0].firstChild.data
order_name = xmldoc.getElementsByTagName('DeliverTo')[0].firstChild.data
street1 = xmldoc.getElementsByTagName('Street1')[0].firstChild.data
state = xmldoc.getElementsByTagName('State')[0].firstChild.data
zip_code = xmldoc.getElementsByTagName('PostalCode')[0].firstChild.data
OUTPUT.append(order_number+' '+order_name+' '+street1+' '+state+' '+zip_code)
print OUTPUT[-1]
OUTPUT = ''.join(OUTPUT)
return (OUTPUT, """<br><br>Quit""")

split a pdf based on outline

i would like to use pyPdf to split a pdf file based on the outline where each destination in the outline refers to a different page within the pdf.
example outline:
main --> points to page 1
sect1 --> points to page 1
sect2 --> points to page 15
sect3 --> points to page 22
it is easy within pyPdf to iterate over each page of the document or each destination in the document's outline; however, i cannot figure out how to get the page number where the destination points.
does anybody know how to find the referencing page number for each destination in the outline?

I figured it out:
class Darrell(pyPdf.PdfFileReader):
def getDestinationPageNumbers(self):
def _setup_outline_page_ids(outline, _result=None):
if _result is None:
_result = {}
for obj in outline:
if isinstance(obj, pyPdf.pdf.Destination):
_result[(id(obj), obj.title)] = obj.page.idnum
elif isinstance(obj, list):
_setup_outline_page_ids(obj, _result)
return _result
def _setup_page_id_to_num(pages=None, _result=None, _num_pages=None):
if _result is None:
_result = {}
if pages is None:
_num_pages = []
pages = self.trailer["/Root"].getObject()["/Pages"].getObject()
t = pages["/Type"]
if t == "/Pages":
for page in pages["/Kids"]:
_result[page.idnum] = len(_num_pages)
_setup_page_id_to_num(page.getObject(), _result, _num_pages)
elif t == "/Page":
_num_pages.append(1)
return _result
outline_page_ids = _setup_outline_page_ids(self.getOutlines())
page_id_to_page_numbers = _setup_page_id_to_num()
result = {}
for (_, title), page_idnum in outline_page_ids.iteritems():
result[title] = page_id_to_page_numbers.get(page_idnum, '???')
return result
pdf = Darrell(open(PATH-TO-PDF, 'rb'))
template = '%-5s %s'
print template % ('page', 'title')
for p,t in sorted([(v,k) for k,v in pdf.getDestinationPageNumbers().iteritems()]):
print template % (p+1,t)

This is just what I was looking for. Darrell's additions to PdfFileReader should be part of PyPDF2.
I wrote a little recipe that uses PyPDF2 and sejda-console to split a PDF by bookmarks. In my case there are several Level 1 sections that I want to keep together. This script allows me to do that and give the resulting files meaningful names.
import operator
import os
import subprocess
import sys
import time
import PyPDF2 as pyPdf
# need to have sejda-console installed
# change this to point to your installation
sejda = 'C:\\sejda-console-1.0.0.M2\\bin\\sejda-console.bat'
class Darrell(pyPdf.PdfFileReader):
...
if __name__ == '__main__':
t0= time.time()
# get the name of the file to split as a command line arg
pdfname = sys.argv[1]
# open up the pdf
pdf = Darrell(open(pdfname, 'rb'))
# build list of (pagenumbers, newFileNames)
splitlist = [(1,'FrontMatter')] # Customize name of first section
template = '%-5s %s'
print template % ('Page', 'Title')
print '-'*72
for t,p in sorted(pdf.getDestinationPageNumbers().iteritems(),
key=operator.itemgetter(1)):
# Customize this to get it to split where you want
if t.startswith('Chapter') or \
t.startswith('Preface') or \
t.startswith('References'):
print template % (p+1, t)
# this customizes how files are renamed
new = t.replace('Chapter ', 'Chapter')\
.replace(': ', '-')\
.replace(': ', '-')\
.replace(' ', '_')
splitlist.append((p+1, new))
# call sejda tools and split document
call = sejda
call += ' splitbypages'
call += ' -f "%s"'%pdfname
call += ' -o ./'
call += ' -n '
call += ' '.join([str(p) for p,t in splitlist[1:]])
print '\n', call
subprocess.call(call)
print '\nsejda-console has completed.\n\n'
# rename the split files
for p,t in splitlist:
old ='./%i_'%p + pdfname
new = './' + t + '.pdf'
print 'renaming "%s"\n to "%s"...'%(old, new),
try:
os.remove(new)
except OSError:
pass
try:
os.rename(old, new)
print' succeeded.\n'
except:
print' failed.\n'
print '\ndone. Spliting took %.2f seconds'%(time.time() - t0)

Small update to #darrell class to be able to parse UTF-8 outlines, which I post as answer because comment would be hard to read.
Problem is in pyPdf.pdf.Destination.title which may be returned in two flavors:
pyPdf.generic.TextStringObject
pyPdf.generic.ByteStringObject
so that output from _setup_outline_page_ids() function returns also two different types for title object, which fails with UnicodeDecodeError if outline title contains anything then ASCII.
I added this code to solve the problem:
if isinstance(title, pyPdf.generic.TextStringObject):
title = title.encode('utf-8')
of whole class:
class PdfOutline(pyPdf.PdfFileReader):
def getDestinationPageNumbers(self):
def _setup_outline_page_ids(outline, _result=None):
if _result is None:
_result = {}
for obj in outline:
if isinstance(obj, pyPdf.pdf.Destination):
_result[(id(obj), obj.title)] = obj.page.idnum
elif isinstance(obj, list):
_setup_outline_page_ids(obj, _result)
return _result
def _setup_page_id_to_num(pages=None, _result=None, _num_pages=None):
if _result is None:
_result = {}
if pages is None:
_num_pages = []
pages = self.trailer["/Root"].getObject()["/Pages"].getObject()
t = pages["/Type"]
if t == "/Pages":
for page in pages["/Kids"]:
_result[page.idnum] = len(_num_pages)
_setup_page_id_to_num(page.getObject(), _result, _num_pages)
elif t == "/Page":
_num_pages.append(1)
return _result
outline_page_ids = _setup_outline_page_ids(self.getOutlines())
page_id_to_page_numbers = _setup_page_id_to_num()
result = {}
for (_, title), page_idnum in outline_page_ids.iteritems():
if isinstance(title, pyPdf.generic.TextStringObject):
title = title.encode('utf-8')
result[title] = page_id_to_page_numbers.get(page_idnum, '???')
return result

Darrell's class can be modified slightly to produce a multi-level table of contents for a pdf (in the manner of pdftoc in the pdftk toolkit.)
My modification adds one more parameter to _setup_page_id_to_num, an integer "level" which defaults to 1. Each invocation increments the level. Instead of storing just the page number in the result, we store the pair of page number and level. Appropriate modifications should be applied when using the returned result.
I am using this to implement the "PDF Hacks" browser-based page-at-a-time document viewer with a sidebar table of contents which reflects LaTeX section, subsection etc bookmarks. I am working on a shared system where pdftk can not be installed but where python is available.

A solution 10 years later for newer python and PyPDF:
from PyPDF2 import PdfReader, PdfWriter
filename = "main.pdf"
with open(filename, "rb") as f:
r = PdfReader(f)
bookmarks = list(map(lambda x: (x.title, r.get_destination_page_number(x)), r.outline))
print(bookmarks)
for i, b in enumerate(bookmarks):
begin = b[1]
end = bookmarks[i+1][1] if i < len(bookmarks) - 1 else len(r.pages)
# print(len(r.pages[begin:end]))
name = b[0] + ".pdf"
print(f"{name=}: {begin=}, {end=}")
with open(name, "wb") as f:
w = PdfWriter(f)
for p in r.pages[begin:end]:
w.add_page(p)
w.write(f)