Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-22 20:23:12 +00:00
Code Issues Projects Releases Packages Wiki Activity

Merge pull request #71 from cdzombak/cdz/process-pinboard-rss-feeds

Browse source 
Add support for Pinboard and Medium RSS feeds
This commit is contained in:
Nick Sweeting 2018-03-14 16:59:40 -07:00 committed by GitHub
commit cb7a2d1747
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 57 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

58
parse.py
View file

@ -17,6 +17,7 @@ Parsed link schema: {
import re
import json
import xml.etree.ElementTree as etree
from datetime import datetime
@ -36,6 +37,8 @@ def get_parsers(file):
'pinboard': parse_json_export,
'bookmarks': parse_bookmarks_export,
'rss': parse_rss_export,
'pinboard_rss': parse_pinboard_rss_feed,
'medium_rss': parse_medium_rss_feed,
}
def parse_links(path):
@ -49,7 +52,7 @@ def parse_links(path):
links += list(parser_func(file))
if links:
break
except (ValueError, TypeError, IndexError):
except (ValueError, TypeError, IndexError, etree.ParseError):
# parser not supported on this file
pass
@ -169,3 +172,56 @@ def parse_bookmarks_export(html_file):
info['type'] = get_link_type(info)
yield info
def parse_pinboard_rss_feed(rss_file):
"""Parse Pinboard RSS feed files into links"""
rss_file.seek(0)
root = etree.parse(rss_file).getroot()
items = root.findall("{http://purl.org/rss/1.0/}item")
for item in items:
url = item.find("{http://purl.org/rss/1.0/}link").text
tags = item.find("{http://purl.org/dc/elements/1.1/}subject").text
title = item.find("{http://purl.org/rss/1.0/}title").text
ts_str = item.find("{http://purl.org/dc/elements/1.1/}date").text
# Pinboard includes a colon in its date stamp timezone offsets, which
# Python can't parse. Remove it:
if ":" == ts_str[-3:-2]:
ts_str = ts_str[:-3]+ts_str[-2:]
time = datetime.strptime(ts_str, "%Y-%m-%dT%H:%M:%S%z")
info = {
'url': url,
'domain': domain(url),
'base_url': base_url(url),
'timestamp': str(time.timestamp()),
'tags': tags,
'title': title,
'sources': [rss_file.name],
}
info['type'] = get_link_type(info)
yield info
def parse_medium_rss_feed(rss_file):
"""Parse Medium RSS feed files into links"""
rss_file.seek(0)
root = etree.parse(rss_file).getroot()
items = root.find("channel").findall("item")
for item in items:
for child in item:
print(child.tag, child.text)
url = item.find("link").text
title = item.find("title").text
ts_str = item.find("pubDate").text
time = datetime.strptime(ts_str, "%a, %d %b %Y %H:%M:%S %Z")
info = {
'url': url,
'domain': domain(url),
'base_url': base_url(url),
'timestamp': str(time.timestamp()),
'tags': "",
'title': title,
'sources': [rss_file.name],
}
info['type'] = get_link_type(info)
yield info