PaperSpan to Instapaper

instapaper_import.py

"""
Given exports from PaperSpan, Diigo, Pocket, format for import to Instapaper.

Run the script, browse to https://www.instapaper.com/user and select "Import from Instapaper CSV"
"""

import datetime
import csv
import re

OUTPUT_CSV = '/Users/foobar/Downloads/instapaper-import.csv'

# ----------------------------------------------------------------------------
INPUT_PAPERSPAN = '/Users/foobar/Downloads/ps_export.html'

with open(INPUT_PAPERSPAN, 'r') as f:
    html = f.readlines()
entries = [l.strip() for l in html if '<li><a ' in l]
entries = [l for l in entries if 'time_read' not in l]
pat = re.compile(r'<li><a href="(.+?)" time_added="(\d+?)">(.+?)<\/a><\/li>')

output = []
for l in entries:
    result = pat.match(l)
    if not result:
        print(l)
        continue
    url, timestamp, title = result.groups()
    output.append({'URL': url, 'Title': title, 'Selection': '', 
                   'Folder': 'Imported', 'Timestamp': timestamp})

print(f'Formatted {len(output)} entries.')

# ----------------------------------------------------------------------------
INPUT_DIIGO = '/Users/jaime/Downloads/diigo-export.csv'

output = []
with open(INPUT_DIIGO, 'r') as f:
    reader = csv.DictReader(f)
    for r in reader:
        output.append({'URL': r['url'], 'Title': r['title'], 
                       'Selection': '', 'Folder': 'Imported', 
                       'Timestamp': int(datetime.datetime.timestamp(
                                            datetime.datetime.now())*1000)}
                      )  
print(f'Formatted {len(output)} entries.')

# ----------------------------------------------------------------------------
INPUT_POCKET = '/Users/jaime/Downloads/pocket-export.html'

with open(INPUT_POCKET, 'r') as f:
    html = f.readlines()
    
entries = [l.strip() for l in html]
pat_read = re.compile(r'<h1>Read Archive</h1>')
pat = re.compile(r'<li><a href="(.+?)" time_added="(\d+?)" tags="(.*)">(.+?)<\/a><\/li>')

folder = 'Imported'
output = []
for l in entries:
    
    if pat_read.match(l): 
        folder = 'Archive'
    
    result = pat.match(l)
    if not result:
        print('NO MATCH', l)
        continue
    url, timestamp, tags, title = result.groups()
    output.append({'URL': url, 'Title': title, 'Selection': '', 'Folder': folder, 'Timestamp': timestamp})
    
print(f'Formatted {len(output)} entries.')

# ----------------------------------------------------------------------------
with open(OUTPUT_CSV, 'w') as f:
    w = csv.DictWriter(f, output[0].keys())
    w.writeheader()
    w.writerows(output)
    
print(f'Formatting complete. See output file {OUTPUT_CSV}')