Distill.io JSON export file importer (#592)

pull/594/head
dgtlmoon 3 years ago committed by GitHub
parent 18f0b63b7d
commit f28c260576
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -683,44 +683,37 @@ def changedetection_app(config=None, datastore_o=None):
@app.route("/import", methods=['GET', "POST"]) @app.route("/import", methods=['GET', "POST"])
@login_required @login_required
def import_page(): def import_page():
import validators
remaining_urls = [] remaining_urls = []
good = 0
if request.method == 'POST': if request.method == 'POST':
now=time.time() from .importer import import_url_list, import_distill_io_json
urls = request.values.get('urls').split("\n")
# URL List import
if (len(urls) > 5000): if request.values.get('urls') and len(request.values.get('urls').strip()):
flash("Importing 5,000 of the first URLs from your list, the rest can be imported again.") # Import and push into the queue for immediate update check
importer = import_url_list()
for url in urls: importer.run(data=request.values.get('urls'), flash=flash, datastore=datastore)
url = url.strip() for uuid in importer.new_uuids:
url, *tags = url.split(" ") update_q.put(uuid)
# Flask wtform validators wont work with basic auth, use validators package
# Up to 5000 per batch so we dont flood the server
if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
new_uuid = datastore.add_watch(url=url.strip(), tag=" ".join(tags), write_to_disk_now=False)
if new_uuid:
# Straight into the queue.
update_q.put(new_uuid)
good += 1
continue
if len(url.strip()): if len(importer.remaining_data) == 0:
remaining_urls.append(url) return redirect(url_for('index'))
else:
remaining_urls = importer.remaining_data
# Distill.io import
if request.values.get('distill-io') and len(request.values.get('distill-io').strip()):
# Import and push into the queue for immediate update check
d_importer = import_distill_io_json()
d_importer.run(data=request.values.get('distill-io'), flash=flash, datastore=datastore)
for uuid in d_importer.new_uuids:
update_q.put(uuid)
flash("{} Imported in {:.2f}s, {} Skipped.".format(good, time.time()-now,len(remaining_urls)))
datastore.needs_write = True
if len(remaining_urls) == 0:
# Looking good, redirect to index.
return redirect(url_for('index'))
# Could be some remaining, or we could be on GET # Could be some remaining, or we could be on GET
output = render_template("import.html", output = render_template("import.html",
remaining="\n".join(remaining_urls) import_url_list_remaining="\n".join(remaining_urls),
original_distill_json=''
) )
return output return output

@ -149,11 +149,13 @@ class perform_site_check():
# Then we assume HTML # Then we assume HTML
if has_filter_rule: if has_filter_rule:
# For HTML/XML we offer xpath as an option, just start a regular xPath "/.." # For HTML/XML we offer xpath as an option, just start a regular xPath "/.."
if css_filter_rule[0] == '/': if css_filter_rule[0] == '/' or css_filter_rule.startswith('xpath:'):
html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule, html_content=fetcher.content) html_content = html_tools.xpath_filter(xpath_filter=css_filter_rule.replace('xpath:', ''),
html_content=fetcher.content)
else: else:
# CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text # CSS Filter, extract the HTML that matches and feed that into the existing inscriptis::get_text
html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content) html_content = html_tools.css_filter(css_filter=css_filter_rule, html_content=fetcher.content)
if has_subtractive_selectors: if has_subtractive_selectors:
html_content = html_tools.element_removal(subtractive_selectors, html_content) html_content = html_tools.element_removal(subtractive_selectors, html_content)
@ -173,7 +175,6 @@ class perform_site_check():
# Re #340 - return the content before the 'ignore text' was applied # Re #340 - return the content before the 'ignore text' was applied
text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8') text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')
# Re #340 - return the content before the 'ignore text' was applied # Re #340 - return the content before the 'ignore text' was applied
text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8') text_content_before_ignored_filter = stripped_text_from_html.encode('utf-8')

@ -0,0 +1,133 @@
from abc import ABC, abstractmethod
import time
import validators
class Importer():
remaining_data = []
new_uuids = []
good = 0
def __init__(self):
self.new_uuids = []
self.good = 0
self.remaining_data = []
@abstractmethod
def run(self,
data,
flash,
datastore):
pass
class import_url_list(Importer):
"""
Imports a list, can be in <code>https://example.com tag1, tag2, last tag</code> format
"""
def run(self,
data,
flash,
datastore,
):
urls = data.split("\n")
good = 0
now = time.time()
if (len(urls) > 5000):
flash("Importing 5,000 of the first URLs from your list, the rest can be imported again.")
for url in urls:
url = url.strip()
if not len(url):
continue
tags = ""
# 'tags' should be a csv list after the URL
if ' ' in url:
url, tags = url.split(" ", 1)
# Flask wtform validators wont work with basic auth, use validators package
# Up to 5000 per batch so we dont flood the server
if len(url) and validators.url(url.replace('source:', '')) and good < 5000:
new_uuid = datastore.add_watch(url=url.strip(), tag=tags, write_to_disk_now=False)
if new_uuid:
# Straight into the queue.
self.new_uuids.append(new_uuid)
good += 1
continue
# Worked past the 'continue' above, append it to the bad list
if self.remaining_data is None:
self.remaining_data = []
self.remaining_data.append(url)
flash("{} Imported from list in {:.2f}s, {} Skipped.".format(good, time.time() - now, len(self.remaining_data)))
class import_distill_io_json(Importer):
def run(self,
data,
flash,
datastore,
):
import json
good = 0
now = time.time()
self.new_uuids=[]
try:
data = json.loads(data.strip())
except json.decoder.JSONDecodeError:
flash("Unable to read JSON file, was it broken?", 'error')
return
if not data.get('data'):
flash("JSON structure looks invalid, was it broken?", 'error')
return
for d in data.get('data'):
d_config = json.loads(d['config'])
extras = {'title': d['name']}
if len(d['uri']) and good < 5000:
try:
# @todo we only support CSS ones at the moment
if d_config['selections'][0]['frames'][0]['excludes'][0]['type'] == 'css':
extras['subtractive_selectors'] = d_config['selections'][0]['frames'][0]['excludes'][0]['expr']
except KeyError:
pass
except IndexError:
pass
try:
extras['css_filter'] = d_config['selections'][0]['frames'][0]['includes'][0]['expr']
if d_config['selections'][0]['frames'][0]['includes'][0]['type'] == 'xpath':
extras['css_filter'] = 'xpath:' + extras['css_filter']
except KeyError:
pass
except IndexError:
pass
try:
extras['tag'] = ", ".join(d['tags'])
except KeyError:
pass
except IndexError:
pass
new_uuid = datastore.add_watch(url=d['uri'].strip(),
extras=extras,
write_to_disk_now=False)
if new_uuid:
# Straight into the queue.
self.new_uuids.append(new_uuid)
good += 1
flash("{} Imported from Distill.io in {:.2f}s, {} Skipped.".format(len(self.new_uuids), time.time() - now, len(self.remaining_data)))

@ -131,7 +131,7 @@ User-Agent: wonderbra 1.0") }}
<li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li> <li>CSS - Limit text to this CSS rule, only text matching this CSS rule is included.</li>
<li>JSON - Limit text to this JSON rule, using <a href="https://pypi.org/project/jsonpath-ng/">JSONPath</a>, prefix with <code>"json:"</code>, use <code>json:$</code> to force re-formatting if required, <a <li>JSON - Limit text to this JSON rule, using <a href="https://pypi.org/project/jsonpath-ng/">JSONPath</a>, prefix with <code>"json:"</code>, use <code>json:$</code> to force re-formatting if required, <a
href="https://jsonpath.com/" target="new">test your JSONPath here</a></li> href="https://jsonpath.com/" target="new">test your JSONPath here</a></li>
<li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example <code>//*[contains(@class, 'sametext')]</code>, <a <li>XPath - Limit text to this XPath rule, simply start with a forward-slash, example <code>//*[contains(@class, 'sametext')]</code> or <code>xpath://*[contains(@class, 'sametext')]</code>, <a
href="http://xpather.com/" target="new">test your XPath here</a></li> href="http://xpather.com/" target="new">test your XPath here</a></li>
</ul> </ul>
Please be sure that you thoroughly understand how to write CSS or JSONPath, XPath selector rules before filing an issue on GitHub! <a Please be sure that you thoroughly understand how to write CSS or JSONPath, XPath selector rules before filing an issue on GitHub! <a

@ -1,13 +1,23 @@
{% extends 'base.html' %} {% extends 'base.html' %}
{% block content %} {% block content %}
<div class="edit-form"> <script type="text/javascript" src="{{url_for('static_content', group='js', filename='tabs.js')}}" defer></script>
<div class="inner"> <div class="edit-form monospaced-textarea">
<div class="tabs collapsable">
<ul>
<li class="tab" id="default-tab"><a href="#url-list">URL List</a></li>
<li class="tab"><a href="#distill-io">Distill.io</a></li>
</ul>
</div>
<div class="box-wrap inner">
<form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST"> <form class="pure-form pure-form-aligned" action="{{url_for('import_page')}}" method="POST">
<input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/> <input type="hidden" name="csrf_token" value="{{ csrf_token() }}"/>
<div class="tab-pane-inner" id="url-list">
<fieldset class="pure-group"> <fieldset class="pure-group">
<legend> <legend>
Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma (,): Enter one URL per line, and optionally add tags for each URL after a space, delineated by comma
(,):
<br> <br>
<code>https://example.com tag1, tag2, last tag</code> <code>https://example.com tag1, tag2, last tag</code>
<br> <br>
@ -20,10 +30,56 @@
font-family:monospace; font-family:monospace;
white-space: pre; white-space: pre;
overflow-wrap: normal; overflow-wrap: normal;
overflow-x: scroll;" rows="25">{{ remaining }}</textarea> overflow-x: scroll;" rows="25">{{ import_url_list_remaining }}</textarea>
</fieldset>
</div>
<div class="tab-pane-inner" id="distill-io">
<fieldset class="pure-group">
<legend>
Copy and Paste your Distill.io watch 'export' file, this should be a JSON file.</br>
This is <i>experimental</i>, supported fields are <code>name</code>, <code>uri</code>, <code>tags</code>, <code>config:selections</code>, the rest (including <code>schedule</code>) are ignored.
<br/>
<p>
How to export? <a href="https://distill.io/docs/web-monitor/how-export-and-import-monitors/">https://distill.io/docs/web-monitor/how-export-and-import-monitors/</a><br/>
Be sure to set your default fetcher to Chrome if required.</br>
</p>
</legend>
<textarea name="distill-io" class="pure-input-1-2" style="width: 100%;
font-family:monospace;
white-space: pre;
overflow-wrap: normal;
overflow-x: scroll;" placeholder="Example Distill.io JSON export file
{
&quot;client&quot;: {
&quot;local&quot;: 1
},
&quot;data&quot;: [
{
&quot;name&quot;: &quot;Unraid | News&quot;,
&quot;uri&quot;: &quot;https://unraid.net/blog&quot;,
&quot;config&quot;: &quot;{\&quot;selections\&quot;:[{\&quot;frames\&quot;:[{\&quot;index\&quot;:0,\&quot;excludes\&quot;:[],\&quot;includes\&quot;:[{\&quot;type\&quot;:\&quot;xpath\&quot;,\&quot;expr\&quot;:\&quot;(//div[@id='App']/div[contains(@class,'flex')]/main[contains(@class,'relative')]/section[contains(@class,'relative')]/div[@class='container']/div[contains(@class,'flex')]/div[contains(@class,'w-full')])[1]\&quot;}]}],\&quot;dynamic\&quot;:true,\&quot;delay\&quot;:2}],\&quot;ignoreEmptyText\&quot;:true,\&quot;includeStyle\&quot;:false,\&quot;dataAttr\&quot;:\&quot;text\&quot;}&quot;,
&quot;tags&quot;: [],
&quot;content_type&quot;: 2,
&quot;state&quot;: 40,
&quot;schedule&quot;: &quot;{\&quot;type\&quot;:\&quot;INTERVAL\&quot;,\&quot;params\&quot;:{\&quot;interval\&quot;:4447}}&quot;,
&quot;ts&quot;: &quot;2022-03-27T15:51:15.667Z&quot;
}
]
}
" rows="25">{{ original_distill_json }}</textarea>
</fieldset> </fieldset>
</div>
<button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button> <button type="submit" class="pure-button pure-input-1-2 pure-button-primary">Import</button>
</form> </form>
</div> </div>
</div> </div>

@ -5,18 +5,17 @@ import time
from flask import url_for from flask import url_for
from .util import live_server_setup from .util import live_server_setup
def test_setup(client, live_server):
def test_import(client, live_server):
live_server_setup(live_server) live_server_setup(live_server)
def test_import(client, live_server):
# Give the endpoint time to spin up # Give the endpoint time to spin up
time.sleep(1) time.sleep(1)
res = client.post( res = client.post(
url_for("import_page"), url_for("import_page"),
data={ data={
"distill-io": "",
"urls": """https://example.com "urls": """https://example.com
https://example.com tag1 https://example.com tag1
https://example.com tag1, other tag""" https://example.com tag1, other tag"""
@ -26,3 +25,96 @@ https://example.com tag1, other tag"""
assert b"3 Imported" in res.data assert b"3 Imported" in res.data
assert b"tag1" in res.data assert b"tag1" in res.data
assert b"other tag" in res.data assert b"other tag" in res.data
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get( url_for("index"))
res = client.get( url_for("index"))
def xtest_import_skip_url(client, live_server):
# Give the endpoint time to spin up
time.sleep(1)
res = client.post(
url_for("import_page"),
data={
"distill-io": "",
"urls": """https://example.com
:ht000000broken
"""
},
follow_redirects=True,
)
assert b"1 Imported" in res.data
assert b"ht000000broken" in res.data
assert b"1 Skipped" in res.data
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get( url_for("index"))
def test_import_distillio(client, live_server):
distill_data='''
{
"client": {
"local": 1
},
"data": [
{
"name": "Unraid | News",
"uri": "https://unraid.net/blog",
"config": "{\\"selections\\":[{\\"frames\\":[{\\"index\\":0,\\"excludes\\":[],\\"includes\\":[{\\"type\\":\\"xpath\\",\\"expr\\":\\"(//div[@id='App']/div[contains(@class,'flex')]/main[contains(@class,'relative')]/section[contains(@class,'relative')]/div[@class='container']/div[contains(@class,'flex')]/div[contains(@class,'w-full')])[1]\\"}]}],\\"dynamic\\":true,\\"delay\\":2}],\\"ignoreEmptyText\\":true,\\"includeStyle\\":false,\\"dataAttr\\":\\"text\\"}",
"tags": ["nice stuff", "nerd-news"],
"content_type": 2,
"state": 40,
"schedule": "{\\"type\\":\\"INTERVAL\\",\\"params\\":{\\"interval\\":4447}}",
"ts": "2022-03-27T15:51:15.667Z"
}
]
}
'''
# Give the endpoint time to spin up
time.sleep(1)
client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
res = client.post(
url_for("import_page"),
data={
"distill-io": distill_data,
"urls" : ''
},
follow_redirects=True,
)
assert b"Unable to read JSON file, was it broken?" not in res.data
assert b"1 Imported from Distill.io" in res.data
res = client.get( url_for("edit_page", uuid="first"))
assert b"https://unraid.net/blog" in res.data
assert b"Unraid | News" in res.data
# flask/wtforms should recode this, check we see it
# wtforms encodes it like id=&#39 ,but html.escape makes it like id=&#x27
# - so just check it manually :(
#import json
#import html
#d = json.loads(distill_data)
# embedded_d=json.loads(d['data'][0]['config'])
# x=html.escape(embedded_d['selections'][0]['frames'][0]['includes'][0]['expr']).encode('utf-8')
assert b"xpath:(//div[@id=&#39;App&#39;]/div[contains(@class,&#39;flex&#39;)]/main[contains(@class,&#39;relative&#39;)]/section[contains(@class,&#39;relative&#39;)]/div[@class=&#39;container&#39;]/div[contains(@class,&#39;flex&#39;)]/div[contains(@class,&#39;w-full&#39;)])[1]" in res.data
# did the tags work?
res = client.get( url_for("index"))
assert b"nice stuff" in res.data
assert b"nerd-news" in res.data
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
# Clear flask alerts
res = client.get(url_for("index"))

@ -117,3 +117,45 @@ def test_xpath_validation(client, live_server):
follow_redirects=True follow_redirects=True
) )
assert b"is not a valid XPath expression" in res.data assert b"is not a valid XPath expression" in res.data
# actually only really used by the distll.io importer, but could be handy too
def test_check_with_prefix_css_filter(client, live_server):
res = client.get(url_for("api_delete", uuid="all"), follow_redirects=True)
assert b'Deleted' in res.data
# Give the endpoint time to spin up
time.sleep(1)
set_original_response()
# Add our URL to the import page
test_url = url_for('test_endpoint', _external=True)
res = client.post(
url_for("import_page"),
data={"urls": test_url},
follow_redirects=True
)
assert b"1 Imported" in res.data
time.sleep(3)
res = client.post(
url_for("edit_page", uuid="first"),
data={"css_filter": "xpath://*[contains(@class, 'sametext')]", "url": test_url, "tag": "", "headers": "", 'fetch_backend': "html_requests"},
follow_redirects=True
)
assert b"Updated watch." in res.data
time.sleep(3)
res = client.get(
url_for("preview_page", uuid="first"),
follow_redirects=True
)
with open('/tmp/fuck.html', 'wb') as f:
f.write(res.data)
assert b"Some text thats the same" in res.data #in selector
assert b"Some text that will change" not in res.data #not in selector
client.get(url_for("api_delete", uuid="all"), follow_redirects=True)

Loading…
Cancel
Save