modified version of arris-scraper.py that writes data into InfluxDB 2.0.

arris-scraper.py

#!/usr/bin/env python3
# -*- coding: UTF-8 -*-
'''arris-scraper.py (c) 2019 Matthew J Ernisse <[email protected]>
All Rights Reserved.

Load the status page from an Arris/Motorola SB8200 modem, parses the
status page and loads the values into an InfluxDB database.

Redistribution and use in source and binary forms,
with or without modification, are permitted provided
that the following conditions are met:

    * Redistributions of source code must retain the
      above copyright notice, this list of conditions
      and the following disclaimer.
    * Redistributions in binary form must reproduce
      the above copyright notice, this list of conditions
      and the following disclaimer in the documentation
      and/or other materials provided with the distribution.

THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR
TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
'''
import datetime
import math
import requests
import sys
from bs4 import BeautifulSoup
from influxdb_client import InfluxDBClient, Point
from influxdb_client.client.write_api import SYNCHRONOUS

url = "https://us-west-2-1.aws.cloud2.influxdata.com"
org = ""
bucket = ""
token = ""


def parseDownstream(obj):
	channels = []
	channelDescr = []
	channelList = []

	skipNext = 0
	for v in obj:
		if skipNext:
			skipNext -= 1
			continue

		if v.string == "Channel ID":
			skipNext = 7
			continue

		# In case we get the whole bullshit.
		if v.string == "Channel":
			break

		channelDescr.append(v.string)

		if len(channelDescr) == 8:
			channels.append(channelDescr)
			channelDescr = []

	for channel in channels:
		channelDescr = {
			'id': int(channel[0]),
			'status': channel[1],
			'modulation': channel[2],
			'freq': int(channel[3].split()[0]),
			'power': float(channel[4].split()[0]),
			'snr': float(channel[5].split()[0]),
			'corrected': int(channel[6]),
			'uncorrected': int(channel[7])
		}

		channelList.append(channelDescr)

	return channelList


def parseUpstream(obj):
	channels = []
	channelDescr = []
	channelList = []

	skipNext = 0
	for v in obj:
		if skipNext:
			skipNext -= 1
			continue

		if v.string == "Channel":
			skipNext = 6
			continue

		channelDescr.append(v.string)

		if len(channelDescr) == 7:
			channels.append(channelDescr)
			channelDescr = []

	for channel in channels:
		channelDescr = {
			'id': int(channel[0]),
			'channel': int(channel[1]),
			'status': channel[2],
			'type': channel[3],
			'freq': int(channel[4].split()[0]),
			'width': int(channel[5].split()[0]),
			'power': float(channel[6].split()[0]),
		}

		channelList.append(channelDescr)

	return channelList


def sendDownstreamMeasurements(db, channels, timeStamp):
	''' Convert the channelList from parseDownstream to an InfluxDB measurement.
	Field:
		- power
		- snr
		- corrected
		- uncorrected
	Tags:
		- id
		- status
		- modulation
	'''
	measurements = []
	fieldKeys = ['power', 'snr', 'corrected', 'uncorrected']
	tagKeys = ['id', 'status', 'modulation','freq']

	for channel in channels:
		fields = {}
		tags = {}

		for k, v in channel.items():
			if k in fieldKeys:
				fields[k] = v
				continue

			if k in tagKeys:
				tags[k] = v
				continue

		measurements.append({
			'measurement': 'arris_downstream',
			'tags': tags,
			'time': timeStamp,
			'fields': fields,
		})
	db.write(bucket, org, measurements) 

def sendUpstreamMeasurements(db, channels, timeStamp):
	''' Convert the channelList from parseUpstream to an InfluxDB measurement.
	Field:
		- power
	Tags:
		- id
		- channel
		- status
		- type
	'''
	measurements = []
	fieldKeys = ['power']
	tagKeys = ['id', 'channel', 'status', 'type','freq']

	for channel in channels:
		fields = {}
		tags = {}

		for k, v in channel.items():
			if k in fieldKeys:
				fields[k] = v
				continue

			if k in tagKeys:
				tags[k] = v
				continue

		measurements.append({
			'measurement': 'arris_upstream',
			'tags': tags,
			'time': timeStamp,
			'fields': fields,
		})

	db.write(bucket, org, measurements) 

if __name__ == "__main__":
	timeStamp = datetime.datetime.now(datetime.timezone.utc)
	timeStamp = timeStamp.isoformat()

	# We seem to get a different page from the modem if we
	# use the generic requests User-Agent.
	headers = {
		 'User-Agent':
		 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:64.0) Gecko/20100101 Firefox/64.0'
	}

	resp = requests.get(
		"http://192.168.100.1/cmconnectionstatus.html",
		headers=headers
	)
	resp.raise_for_status()

	soup = BeautifulSoup(resp.text, 'lxml')
	infoTables = soup.findAll('table', {'class': 'simpleTable'})

	downstream = infoTables[1]
	upstream = infoTables[2]

	downChannels = parseDownstream(downstream.find_all_next('td'))
	upChannels = parseUpstream(upstream.find_all_next('td'))

	client = InfluxDBClient(url=url, token=token, org=org)

	write_api = client.write_api(write_options=SYNCHRONOUS)

	sendDownstreamMeasurements(write_api, downChannels, timeStamp)
	sendUpstreamMeasurements(write_api, upChannels, timeStamp)