partner scrapper

This commit is contained in:
Benoît Vézina 2023-07-12 07:17:17 -04:00
parent 4a72ee4f6b
commit 0ec4e40c26
9 changed files with 518 additions and 0 deletions

View file

@ -0,0 +1,3 @@
# -*- coding: utf-8 -*-
from . import models

View file

@ -0,0 +1,37 @@
# -*- coding: utf-8 -*-
{
'name': 'Bemade Odoo Partner Scrapper',
'version': '1.0.0',
'category': 'Administration',
'summary': 'Module for scraping partners from odoo.com.',
'description': """
This module enables the scraping of partners from odoo.com. It allows for the collection and management of partner contact information.
Main Features:
* Automatically scrape partners from odoo.com.
* Extracts partner name, website, and contact information.
* Manage contact information of partners.
""",
'sequence': 10,
'license': 'GPL-3',
'author': 'Bemade',
'website': 'https://www.bemade.org',
'depends': ['base', 'contacts', 'sale_management', 'sale' , 'partner_multi_relation'],
'data': [
# No security
'views/res_partner_views.xml',
'data/res_partner_relation_type.xml'
],
"assets": {
"web.assets_backend": [
"bemade_odoo_partner_scrapper/static/src/js/odoo_scrapper.js",
],
"web.assets_qweb": [
"bemade_odoo_partner_scrapper/static/src/xml/odoo_scrapper_templates.xml",
],
},
'demo': [],
'installable': True,
'application': False,
'auto_install': False
}

View file

@ -0,0 +1,106 @@
<?xml version="1.0" encoding="UTF-8" ?>
<odoo>
<!-- Added partner categories and partners to this file, because it
turned out to be a bad idea to rely on demo data in base module,
that can change from release to release. Only dependency on
countries remain. They are less likely to change/disappear.
-->
<!-- Partner relation types -->
<record id="rel_type_assistant" model="res.partner.relation.type">
<field name="name">Is assistant of</field>
<field name="name_inverse">Has assistant</field>
<field name="contact_type_left">p</field>
<field name="contact_type_right">p</field>
</record>
<record id="rel_type_competitor" model="res.partner.relation.type">
<field name="name">Is competitor of</field>
<field name="name_inverse">Is competitor of</field>
<field name="contact_type_left">c</field>
<field name="contact_type_right">c</field>
<field name="is_symmetric" eval="True" />
</record>
<record id="rel_type_has_worked_for" model="res.partner.relation.type">
<field name="name">Has worked for</field>
<field name="name_inverse">Has former employee</field>
<field name="contact_type_left">p</field>
<field name="contact_type_right">c</field>
</record>
<!-- Categories -->
<record id="res_partner_category_pmr_0" model="res.partner.category">
<field name="name">Washing Companies</field>
</record>
<record id="res_partner_category_pmr_4" model="res.partner.category">
<field name="name">Washing Gold</field>
<field name="parent_id" ref="res_partner_category_pmr_0" />
</record>
<record id="res_partner_category_pmr_5" model="res.partner.category">
<field name="name">Washing Silver</field>
<field name="parent_id" ref="res_partner_category_pmr_0" />
</record>
<record id="res_partner_category_pmr_11" model="res.partner.category">
<field name="name">Washing Services</field>
<field name="parent_id" ref="res_partner_category_pmr_0" />
</record>
<!-- Partners -->
<record id="res_partner_pmr_great" model="res.partner">
<field name="name">Great Washing Powder Company</field>
<field
name="category_id"
eval="[(6, 0, [ref('res_partner_category_pmr_11'), ref('res_partner_category_pmr_4')])]"
/>
<field name="is_company">1</field>
<field name="city">Le Bourget du Lac</field>
<field name="zip">73377</field>
<field name="phone">+33 4 49 23 44 54</field>
<field name="country_id" ref="base.fr" />
<field name="street">93, Press Avenue</field>
<field name="email">great@yourcompany.example.com</field>
<field name="website">http://www.great.com</field>
</record>
<record id="res_partner_pmr_best" model="res.partner">
<field name="name">Best Washing Powder Company</field>
<field
name="category_id"
eval="[(6, 0, [ref('res_partner_category_pmr_4'), ref('res_partner_category_pmr_11')])]"
/>
<field name="is_company">1</field>
<field name="city">Champs sur Marne</field>
<field name="zip">77420</field>
<field name="country_id" ref="base.fr" />
<field name="email">best@yourcompany.example.com</field>
<field name="phone">+33 1 64 61 04 01</field>
<field name="street">12 rue Albert Einstein</field>
<field name="website">http://www.best.com/</field>
</record>
<record id="res_partner_pmr_super" model="res.partner">
<field name="name">Super Washing Powder Company</field>
<field name="category_id" eval="[(6,0,[ref('res_partner_category_pmr_5')])]" />
<field name="is_company">1</field>
<field name="street">3rd Floor, Room 3-C,</field>
<field
name="street2"
>Carretera Panamericana, Km 1, Urb. Delgado Chalbaud</field>
<field name="city">Caracas</field>
<field name="zip">1090</field>
<field name="email">super@yourcompany.example.com</field>
<field name="phone">+58 212 681 0538</field>
<field name="country_id" ref="base.ve" />
<field name="website">super.com</field>
</record>
<!-- Relations -->
<record id="rel_1" model="res.partner.relation">
<field name="left_partner_id" ref="res_partner_pmr_great" />
<field name="right_partner_id" ref="res_partner_pmr_super" />
<field name="type_id" ref="rel_type_competitor" />
</record>
<record id="rel_2" model="res.partner.relation">
<field name="left_partner_id" ref="res_partner_pmr_best" />
<field name="right_partner_id" ref="res_partner_pmr_super" />
<field name="type_id" ref="rel_type_competitor" />
</record>
<record id="rel_3" model="res.partner.relation">
<field name="left_partner_id" ref="res_partner_pmr_great" />
<field name="right_partner_id" ref="res_partner_pmr_best" />
<field name="type_id" ref="rel_type_competitor" />
</record>
</odoo>

View file

@ -0,0 +1,36 @@
<?xml version="1.0" encoding="UTF-8" ?>
<odoo>
<!-- Added partner categories and partners to this file, because it
turned out to be a bad idea to rely on demo data in base module,
that can change from release to release. Only dependency on
countries remain. They are less likely to change/disappear.
-->
<!-- Partner relation types -->
<record id="rel_type_odoo_partner" model="res.partner.relation.type">
<field name="name">Is Odoo Partner Of</field>
<field name="name_inverse">Is Odoo Client Of</field>
<field name="contact_type_left">c</field>
<field name="contact_type_right">c</field>
</record>
<!-- Categories -->
<record id="res_partner_category_odoo_partner" model="res.partner.category">
<field name="name">Odoo Partner</field>
</record>
<record id="res_partner_category_odoo_partner_learning" model="res.partner.category">
<field name="name">Learning Partner</field>
<field name="parent_id" ref="res_partner_category_odoo_partner" />
</record>
<record id="res_partner_category_odoo_partner_ready" model="res.partner.category">
<field name="name">Ready Partner</field>
<field name="parent_id" ref="res_partner_category_odoo_partner" />
</record>
<record id="res_partner_category_odoo_partner_silver" model="res.partner.category">
<field name="name">Silver Partner</field>
<field name="parent_id" ref="res_partner_category_odoo_partner" />
</record>
<record id="res_partner_category_odoo_partner_gold" model="res.partner.category">
<field name="name">Gold Partner</field>
<field name="parent_id" ref="res_partner_category_odoo_partner" />
</record>
</odoo>

View file

@ -0,0 +1,3 @@
# -*- coding: utf-8 -*-
from . import res_partner

View file

@ -0,0 +1,197 @@
from odoo import models, fields, api, _
import requests
from bs4 import BeautifulSoup
import logging
_logger = logging.getLogger(__name__)
class ResPartner(models.Model):
_inherit = 'res.partner'
is_odoo_partner = fields.Boolean(string="Is Odoo Partner", default=False, tracking=True)
is_odoo_user = fields.Boolean(string="Is Odoo User", default=False, tracking=True)
odoo_name = fields.Char(string="Name on Odoo", tracking=True)
odoo_id = fields.Char(string="ID on Odoo", tracking=True)
odoo_url = fields.Char(string="Odoo Partner URL", tracking=True, index=True)
@api.model
def get_odoo_partner(self):
def extract_partner_data(url):
page = requests.get("https://www.odoo.com" + url)
soup = BeautifulSoup(page.content, 'html.parser')
partner_data = {}
partner_data['name'] = soup.find(id="partner_name").text
partner_data['odoo_name'] = soup.find(id="partner_name").text
address_div = soup.find('span', itemprop='streetAddress')
email_div = soup.find('span', itemprop='email')
phone_div = soup.find('span', itemprop='telephone')
website_div = soup.find('span', itemprop='website')
if address_div is not None:
# Extract address components
address_parts = address_div.get_text(separator="\n").split("\n")
partner_data['street'] = address_parts[0]
city_state_postal = address_parts[len(address_parts) - 2].split(', ')
if city_state_postal != [',']:
partner_data['city'] = city_state_postal[0]
state_postal = city_state_postal[1].split(' ')
if len(state_postal) == 3 and len(state_postal[2]) == 3:
partner_data['zip'] = state_postal[1] + state_postal[2]
state_data = state_postal[0]
elif len(state_postal) == 2 and state_postal[1]:
if len(state_postal[1]) == 6:
partner_data['zip'] = state_postal[1]
state_data = state_postal[0]
if len(state_postal[1]) == 3:
if len(state_postal[0]) == 2:
partner_data['zip'] = state_postal[1]
state_data = state_postal[0]
else:
partner_data['zip'] = state_postal[0] + state_postal[1]
else:
if len(state_postal[0]) == 6:
partner_data['zip'] = state_postal[0]
else:
state_data = state_postal[0]
# partner_data['country'] = address_parts[len(address_parts) - 1]
partner_data['email'] = email_div.string if email_div and email_div.string else ''
partner_data['phone'] = phone_div.string if phone_div and phone_div.string else ''
partner_data['website'] = website_div.string if website_div and website_div.string else ''
partner_data['is_odoo_partner'] = True
partner_data['is_odoo_user'] = True
if state_data:
partner_data['state_id'] = self.env['res.country.state'].search([('code', '=', state_data)]).id
return partner_data
# Load the webpage at the given url
page = requests.get("https://www.odoo.com/fr_FR/partners/country/canada-36")
# Parse the HTML content
soup = BeautifulSoup(page.content, 'html.parser')
div = soup.find(id="ref_content")
partners_url = set()
other_pages = set()
for link in div.find_all('a'):
href = link.get('href')
if href is not None:
# Ignore any URL containing 'country/canada-36'
if '/page/' in href:
# Add to set. Duplicates will be ignored automatically.
other_pages.add(href)
for link in div.find_all('a'):
href = link.get('href')
if href is not None and href != '':
# Ignore any URL containing 'country/canada-36'
if 'country/canada-36' not in href:
# Add to set. Duplicates will be ignored automatically.
partners_url.add(href.split('#', 1)[0].split('?', 1)[0])
for other_page in other_pages:
page = requests.get("https://www.odoo.com" + other_page)
soup = BeautifulSoup(page.content, 'html.parser')
div = soup.find(id="ref_content")
for link in div.find_all('a'):
href = link.get('href')
if href is not None and href != '':
# Ignore any URL containing 'country/canada-36'
if 'country/canada-36' not in href:
# Add to set. Duplicates will be ignored automatically.
partners_url.add(href.split('#', 1)[0].split('?', 1)[0])
for partner_url in partners_url:
page = requests.get("https://www.odoo.com" + partner_url)
soup = BeautifulSoup(page.content, 'html.parser')
odoo_partner = extract_partner_data(partner_url)
print (odoo_partner)
# partner_name = soup.find(id="partner_name").text
# address_div = soup.find('span', itemprop='streetAddress')
# email_div = soup.find('span', itemprop='email')
# phone_div = soup.find('span', itemprop='telephone')
# website_div = soup.find('span', itemprop='website')
# if address_div is not None:
# # Extract address components
# address_parts = address_div.get_text(separator="\n").split("\n")
# street_address = address_parts[0]
# city_state_postal = address_parts[len(address_parts) - 2].split(', ')
#
# if city_state_postal != [',']:
# city = city_state_postal[0]
# state_postal = city_state_postal[1].split(' ')
#
# if len(state_postal) == 3 and len(state_postal[2]) == 3:
# postal_code = state_postal[1] + state_postal[2]
# state = state_postal[0]
# elif len(state_postal) == 2 and state_postal[1]:
# if len(state_postal[1]) == 6:
# postal_code = state_postal[1]
# state = state_postal[0]
# if len(state_postal[1]) == 3:
# if len(state_postal[0]) == 2:
# postal_code = state_postal[1]
# state = state_postal[0]
# else:
# postal_code = state_postal[0] + state_postal[1]
# state = ''
# else:
# if len(state_postal[0]) == 6:
# postal_code = state_postal[0]
# state = ''
# else:
# postal_code = ''
# state = state_postal[0]
# else:
# city = ''
# state = ''
# postal_code = ''
# # state = state_postal[0]
# # postal_code = state_postal[1] + state_postal[2]
# country = address_parts[len(address_parts) - 1]
# if email_div and email_div.string:
# email = email_div.string
# else:
# email = ''
# if phone_div and phone_div.string:
# phone = phone_div.string
# else:
# phone = ''
# if website_div and website_div.string:
# website = website_div.string
# else:
# website = ''
_logger.info(f"Processing {odoo_partner['name']} with email {odoo_partner['email']} and phone {odoo_partner['phone']} and website {odoo_partner['website']}")
exist_odoo_name = self.env['res.partner'].search([('odoo_name', '=', odoo_partner['odoo_name'])])
if not exist_odoo_name:
exist_email = self.env['res.partner'].search([('email', '=', odoo_partner['email'])])
if not exist_email:
exist_phone = self.env['res.partner'].search([('phone', '=', odoo_partner['phone'])])
if not exist_phone:
exist_website = self.env['res.partner'].search([('website', '=', odoo_partner['website'])])
if not exist_website or odoo_partner['website'] == '':
self.env['res.partner'].create(odoo_partner)
# self.env['res.partner'].create({
# 'name': partner_name,
# 'street': street_address,
# 'city': city,
# 'state_id': state_id.id if state_id else False,
# 'zip': postal_code,
# 'country_id': country_id.id if country_id else False,
# 'email': email,
# 'phone': phone,
# 'website': website,
# 'is_odoo_partner': True,
# })

View file

@ -0,0 +1,71 @@
/** @odoo-module **/
import ListController from 'web.ListController';
import ListView from 'web.ListView';
import KanbanController from 'web.KanbanController';
import KanbanView from 'web.KanbanView';
const viewRegistry = require('web.view_registry');
const OdooScrapperListController = ListController.extend({
// buttons_template must match the t-name on the template for the button (static xml)
buttons_template: 'odoo_scrapper.list_view_buttons',
events: _.extend({}, ListController.prototype.events, {
'click .o_button_get_partner': '_onGetPartnerClick',
}),
// This may need to be async function() if there needs to be an await this._rpc({ ... }); call to not reload early
_onGetPartnerClick: function () {
this._rpc({
model: 'res.partner',
method: 'get_odoo_partner',
args: [],
}).then(() => {
this.reload();
});
// Couldn't test this for real, but it runs the action. May need a this.reload()
},
});
const OdooScrapperListView = ListView.extend({
config: _.extend({}, ListView.prototype.config, {
Controller: OdooScrapperListController,
}),
});
// key must match with the js_class attribute of the tree view you want to modify
viewRegistry.add('res_partner_odoo_scrapper_tree', OdooScrapperListView);
const OdooScrapperKanbanController = KanbanController.extend({
// buttons_template must match the t-name on the template for the button (static xml)
buttons_template: 'odoo_scrapper.kanban_view_buttons',
events: _.extend({}, KanbanController.prototype.events, {
'click .o_button_get_partner': '_onGetPartnerClick',
}),
// This may need to be async function() if there needs to be an await this._rpc({ ... }); call to not reload early
_onGetPartnerClick: function () {
this._rpc({
model: 'res.partner',
method: 'get_odoo_partner',
args: [],
}).then(() => {
this.reload();
});
// Couldn't test this for real, but it runs the action. May need a this.reload()
},
});
const OdooScrapperKanbanView = KanbanView.extend({
config: _.extend({}, KanbanView.prototype.config, {
Controller: OdooScrapperKanbanController,
}),
});
// key must match with the js_class attribute of the tree view you want to modify
viewRegistry.add('res_partner_odoo_scrapper_kanban', OdooScrapperKanbanView);

View file

@ -0,0 +1,24 @@
<?xml version="1.0" encoding="UTF-8" ?>
<templates id="template" xml:space="preserve">
<t t-extend="ListView.buttons" t-name="odoo_scrapper.list_view_buttons"> <!-- t-name must match with js controller button template -->
<t t-jquery="button.o_list_button_add" t-operation="after">
<button type="button"
class="btn btn-primary ml4 o_button_get_partner"
title="Get Odoo Partner"> Get Odoo Partner </button>
</t>
</t>
<t t-extend="KanbanView.buttons" t-name="odoo_scrapper.kanban_view_buttons">
<t t-jquery="button" t-operation="after">
<button type="button"
class="btn btn-primary ml4 o_button_get_partner"
title="Get Odoo Partner"> Get Odoo Partner </button>
</t>
</t>
</templates>

View file

@ -0,0 +1,41 @@
<?xml version="1.0" encoding="utf-8"?>
<odoo>
<record id="view_partner_tree_inherit" model="ir.ui.view">
<field name="name">res.partner.tree.inherit</field>
<field name="model">res.partner</field>
<field name="inherit_id" ref="base.view_partner_tree"/>
<field name="arch" type="xml">
<xpath expr="//tree" position="attributes">
<attribute name="js_class">res_partner_odoo_scrapper_tree</attribute>
</xpath>
<xpath expr="//tree" position="inside">
<field name="is_odoo_partner"/>
</xpath>
</field>
</record>
<record id="view_partner_kanban_inherit" model="ir.ui.view">
<field name="name">res.partner.kanban.inherit</field>
<field name="model">res.partner</field>
<field name="inherit_id" ref="base.res_partner_kanban_view"/>
<field name="arch" type="xml">
<xpath expr="//kanban" position="attributes">
<attribute name="js_class">res_partner_odoo_scrapper_kanban</attribute>
</xpath>
</field>
</record>
<record model="ir.ui.view" id="view_res_partner_odoo_search">
<field name="name">res.partner.odoo.search</field>
<field name="model">res.partner</field>
<field name="inherit_id" ref="base.view_res_partner_filter"/>
<field name="arch" type="xml">
<filter name="type_company" position="after">
<filter domain="[('is_odoo_partner','=','True')]" string="Odoo Partners" name="res_partner_odoo_partner_filter"/>
<filter domain="[('is_odoo_user','=','True')]" string="Odoo Users" name="res_partner_odoo_user_filter"/>
</filter>
</field>
</record>
</odoo>