Scrapy - Scrapper un site Odoo

Scrapy - Scrapper un site Odoo

https://scrapeops.io/python-scrapy-playbook/scrapy-login-form/

context.py

from OpenSSL import SSL
from scrapy.core.downloader.contextfactory import ScrapyClientContextFactory


class CustomContextFactory(ScrapyClientContextFactory):
    """
    Custom context factory that allows SSL negotiation.
    """

    def __init__(self):
        # Use SSLv23_METHOD so we can use protocol negotiation
        self.method = SSL.SSLv23_METHOD

items.py

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class BurdaItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    id_product = scrapy.Field()
    product_name = scrapy.Field()
    full_description = scrapy.Field()
    price_ttc = scrapy.Field()
    image_cover = scrapy.Field()
    pass

middlewares.py

# Define here the models for your spider middleware
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals

# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter


class BurdaSpiderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, or item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request or item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class BurdaDownloaderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.

    @classmethod
    def from_crawler(cls, crawler):
        # This method is used by Scrapy to create your spiders.
        s = cls()
        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
        return s

    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.

        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

pipelines.py

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
import MySQLdb
import re

class BurdaPipeline:
    host='127.0.0.1'
    user='root'
    passwd='HgdgfTgdf562'
    db='burda'

    def __init__(self):
        print("Opening connection mysql...")
        self.connection = MySQLdb.connect(self.host, self.user, self.passwd, self.db,use_unicode=True, charset="utf8")
        self.cursor = self.connection.cursor()
        print("success connect bdd...")

    def process_item(self, item, spider):
        
        imagetest=''
        for imgs in item['image_cover'] :
            imagetest  = 'https://activa-france.com'
            imagetest  = imgs
            imagetest  = ','
        

        
        try:
            sql = "INSERT INTO burda_product VALUES (%s,%s,%s,%s,%s) ON DUPLICATE KEY UPDATE id_product=%s,product_name=%s,price_ttc=%s,full_description=%s,image_cover=%s"
            self.cursor.execute(sql,(item['id_product'],item['product_name'],item['price_ttc'],item['full_description'],imagetest,item['id_product'],item['product_name'],item['price_ttc'],item['full_description'],imagetest))
            self.connection.commit()
        except MySQLdb.Error as e:
            print("Error %d: %s" % (e.args[0], e.args[1]))
        return item

settings.py

# Scrapy settings for burda project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'burda'

SPIDER_MODULES = ['burda.spiders']
NEWSPIDER_MODULE = 'burda.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (compatible; Googlebot/2.1;  http://www.google.com/bot.html)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'burda.middlewares.BurdaSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'burda.middlewares.BurdaDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    'burda.pipelines.BurdaPipeline': 300,
}
#DOWNLOADER_CLIENTCONTEXTFACTORY = 'burda.context.CustomContextFactory'
#DOWNLOAD_HANDLERS = {
#  's3': None,
#}


# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

mybot.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from scrapy.spiders import CrawlSpider
from scrapy.linkextractors import LinkExtractor
from burda.items import BurdaItem
from scrapy.selector import Selector
from scrapy.http import Request


class Burda(CrawlSpider):
    name="burda"
    #on autorise seulement le crawl du site indiqué dans allowed_domains
    allowed_domains = ['activa-france.com']
    # on definit l'id du produit de départ
    start_id_product =157513
    #100000
    # on definit l'id du produit de fin
    end_id_product =157514
    #636278

    #on boucle la requete sur la rangée d'id
    def start_requests(self):
        for i in range(self.start_id_product,self.end_id_product):
         yield Request('https://activa-france.com/shop/product/%s' % i , callback=self.parse_items)
    def parse_items(self,response):
        #récupération des datas récoltées (contenu de la page produit)
        sel = Selector(response)

        #on prépare item
        item = BurdaItem()
        item['id_product'] = sel.xpath('//input[@name="product_id"]/@value').extract() or [None][0]
        item['product_name'] = sel.xpath('//h1[@itemprop="name"]/text()').extract() or [None][0]
        item['full_description'] = sel.xpath('//div[@id="product_full_description"]').extract_first() or [None][0]
        item['price_ttc'] = sel.xpath('//span[@itemprop="price"]/text()').extract() or [None][0]
        images = sel.xpath('//div[@id="o-carousel-product"]/div/div/div/img/@src').extract() or [None][0]
        item['image_cover'] = images



        

        return item