1. 什么是 Scrapy CrawlSpider?
CrawlSpider 是 Scrapy 的派生类,Spider 类的设计原则是只抓取 start_url 列表中的网页。相比之下,CrawlSpider 类定义了一些规则,为跟踪链接提供了一种方便的机制--从刮擦中提取链接 亚马逊 网页并继续抓取。
CrawlSpider 可以匹配符合特定条件的 URL,将其组合成 Request 对象,并在指定回调函数的同时自动将其发送给引擎。换句话说,CrawlSpider 爬虫可以根据预定义的规则自动检索连接。
2. 创建用于搜索亚马逊的 CrawlSpider 爬虫
scrapy genspider -t crawl spider_name domain_name
创建 Scraping Amazon 爬虫命令:
例如,创建一个名为 "amazonTop "的亚马逊爬虫:
scrapy genspider -t crawl amzonTop amazon.com
下面的文字就是整个代码:
导入 scrapy
从 scrapy.linkextractors 导入 LinkExtractor
从 scrapy.spiders 导入 CrawlSpider、Rule
类 TSpider(CrawlSpider):
name = 'amzonTop
allowed_domains = ['amazon.com']
start_urls = ['https://amazon.com/']
rules = (
Rule(LinkExtractor(allow=r'Items/'), callback='parse_item', follow=True)、
)
def parse_item(self, response):
item = {}
# item['domain_id'] = response.xpath('//input[@id="sid"]/@value').get()
# item['name'] = response.xpath('//div[@id="name"]').get()
# item['description'] = response.xpath('//div[@id="description"]').get()
返回 item
Rules 是包含 Rule 对象的元组或列表。规则由 LinkExtractor、callback 和 follow 等参数组成。
A.链接提取器 链接提取器,可使用 regex、XPath 或 CSS 匹配 URL 地址。
B. 回调: 提取 URL 地址的回调函数,可选。
C. 遵循: 表示与提取的 URL 地址相对应的响应是否将继续由规则处理。true "表示继续处理,"false "表示不继续处理。
3. 搜索亚马逊产品数据
3.1 创建亚马逊抓取爬虫
scrapy genspider -t crawl amazonTop2 amazon.com
蜘蛛代码的结构:
3.2 提取用于分页产品列表和产品详细信息的 URL。
A.从产品列表页面提取所有产品的阿信和排名,即从产品列表页面的 蓝箱 在图像中。
B.从产品详细信息页面提取所有颜色和规格的 Asin,即从 绿箱其中包括蓝色方框中的阿信。
绿色方框:如购物网站中衣服的 X 号、M 号、L 号、XL 号和 XXL 号。
蜘蛛文件:amzonTop2.py
导入日期时间
导入时间
导入时间
从 copy 导入 deepcopy
导入 scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
类 Amazontop2Spider(CrawlSpider):
name = 'amazonTop2
allowed_domains = ['amazon.com'] (允许域
# https://www.amazon.com/Best-Sellers-Tools-Home-Improvement-Wallpaper/zgbs/hi/2242314011/ref=zg_bs_pg_2?_encoding=UTF8&pg=1
start_urls = ['https://amazon.com/Best-Sellers-Tools-Home-Improvement-Wallpaper/zgbs/hi/2242314011/ref=zg_bs_pg_2']
rules = [
Rule(LinkExtractor(restrict_css=('.a-selected','.a-normal')), callback='parse_item', follow=True)、
]
def parse_item(self, response):
asin_list_str = "".join(response.xpath('//div[@class="p13n-desktop-grid"]/@data-client-recs-list').extract())
if asin_list_str:
asin_list = eval(asin_list_str)
for asinDict in asin_list:
item = {}
如果 str(asinDict) 中有"'id'",则
listProAsin = asinDict['id']
pro_rank = asinDict['元数据图']['render.zg.rank']
item['rank'] = pro_rank
item['ListAsin'] = listProAsin
item['rankAsinUrl'] =f "https://www.amazon.com/Textile-Decorative-Striped-Corduroy-Pillowcases/dp/{listProAsin}/ref=zg_bs_3732341_sccl_1/136-3072892-8658650?psc=1"
打印("-"*30)
打印(项目)
print('-'*30)
yield scrapy.Request(item["rankAsinUrl"], callback=self.parse_list_asin、
meta={"main_info": deepcopy(item)})
def parse_list_asin(self, response):
"""
:param response:
:return:
"""
news_info = response.meta["main_info"]
list_ASIN_all_findall = re.findall('"colorToAsin":(.*?), "refactorEnabled":true,', str(response.text))
try:
try:
parentASIN = re.findall(r', "parentAsin":"(.*?)",', str(response.text))[-1]
except:
parentASIN = re.findall(r'&parentAsin=(.*?)&', str(response.text))[-1]
except:
parentASIN = ''
# parentASIN = parentASIN[-1] if parentASIN !=[] else ""
print("parentASIN:",parentASIN)
如果 list_ASIN_all_findall:
list_ASIN_all_str = "".join(list_ASIN_all_findall)
list_ASIN_all_dict = eval(list_ASIN_all_str)
for asin_min_key, asin_min_value in list_ASIN_all_dict.items():
if asin_min_value:
asin_min_value = asin_min_value['asin']。
news_info['parentASIN'] = parentASIN
news_info['secondASIN'] = asin_min_value
news_info['rankSecondASINUrl'] = f "https://www.amazon.com/Textile-Decorative-Striped-Corduroy-Pillowcases/dp/{asin_min_value}/ref=zg_bs_3732341_sccl_1/136-3072892-8658650?psc=1"
yield scrapy.Request(news_info["rankSecondASINUrl"], callback=self.parse_detail_info,meta={"news_info": deepcopy(news_info)})
def parse_detail_info(self, response):
"""
:param response:
:return:
"""
item = response.meta['news_info']
ASIN = item['secondASIN']
# print('--------------------------------------------------------------------------------------------')
# with open('amazon_h.html', 'w') as f:
# f.write(response.body.decode())
# print('--------------------------------------------------------------------------------------------')
pro_details = response.xpath('//table[@id="productDetails_detailBullets_sections1"]//tr')
pro_detail = {}
for pro_detail.xpath( //table[@id="productDetails_detailBullets_sections1"]//tr')
pro_detail[pro_row.xpath('./th/text()').extract_first().strip()] = pro_row.xpath('./td//text()').extract_first().strip()
print("pro_detail",pro_detail)
ships_from_list = response.xpath(
'//div[@tabular-attribute-name="Ships from"]/div//span//text()').extract()
# 物流方
尝试:
delivery = ships_from_list[-1]
except:
delivery = ""
seller = "".join(response.xpath('//div[@id="tabular-buybox"]//div[@class="tabular-buybox-text"][3]//text()').extract()).strip().replace("'", "")
if seller == "":
seller = "".join(response.xpath('//div[@class="a-section a-spacing-base"]/div[2]/a/text()').extract().strip().replace("'", "")
seller_link_str = "".join(response.xpath('//div[@id="tabular-buybox"]//div[@class="tabular-buybox-text"][3]//a/@href').extract())
# if seller_link_str:
# seller_link = "https://www.amazon.com"+ seller_link_str
# 否则
# seller_link = ''
seller_link = "https://www.amazon.com"+ seller_link_str if seller_link_str else ''
brand_link = response.xpath('//div[@id="bylineInfo_feature_div"]/div[@class="a-section a-spacing-none"]/a/@href').extract_first()
pic_link = response.xpath('//div[@id="main-image-container"]/ul/li[1]//img/@src').extract_first()
title = response.xpath('//div[@id="titleSection"]/h1//text()').extract_first()
star = response.xpath('//div[@id="averageCustomerReviews_feature_div"]/div[1]//span[@class="a-iconalt"]//text()').extract_first().strip()
try:
price = response.xpath('//div[@class="a-section a-spacing-none aok-align-center"]/span[2]/span[@class="a-offscreen"]//text()').extract_first()
except:
try:
price = response.xpath('//div[@class="a-section a-spacing-none aok-align-center"]/span[1]/span[@class="a-offscreen"]//text()').extract_first()
except:
price = ''
size = response.xpath('//li[@class="swatchSelect"]//p[@class="a-text-left a-size-base"]//text()').extract_first()
key_v = str(pro_detail.keys())
brand = pro_detail['品牌'],如果 key_v 中有 "品牌",否则为''
如果 brand == '':
brand = response.xpath('//tr[@class="a-spacing-small po-brand"]/td[2]//text()').extract_first().strip()
elif brand == "":
brand = response.xpath('//div[@id="bylineInfo_feature_div"]/div[@class="a-section a-spacing-none"]/a/text()').extract_first().replace("Brand: ", "").replace("Visit the", "").replace("Store", '').strip()
color = pro_detail['颜色'],如果 key_v 中有 "颜色",否则为""
如果 color == "":
color = response.xpath('//tr[@class="a-spacing-small po-color"]/td[2]//text()').extract_first()
elif color == '':
color = response.xpath('//div[@id="variation_color_name"]/div[@class="a-row"]/span//text()').extract_first()
pattern = pro_detail['Pattern'] if "Pattern" in key_v else ""
如果 pattern == "":
pattern = response.xpath('//tr[@class="a-spacing-small po-pattern"]/td[2]//text()').extract_first().strip()
# 材料
try:
material = pro_detail['材料']
except:
material = response.xpath('//tr[@class="a-spacing-small po-material"]/td[2]//text()').extract_first().strip()
# 形状
shape = pro_detail['形状'],如果 key_v 中有 "形状",否则为""
如果 shape == "":
shape = response.xpath('//tr[@class="a-spacing-small po-item_shape"]/td[2]//text()').extract_first().strip()
# 样式
# five_points
five_points =response.xpath('//div[@id="feature-bullets"]/ul/li[position()>1]//text()').extract_first().replace("\"", "'")
size_num = len(response.xpath('//div[@id="variation_size_name"]/ul/li').extract())
color_num = len(response.xpath('//div[@id="variation_color_name"]//li').extract())
# variant_num =
# 样式
# 制造商
try:
Manufacturer = pro_detail['制造商'],if "Manufacturer" in str(pro_detail) else " "
except:
制造商 = ""
item_weight = pro_detail['Item Weight'] if "Weight" in str(pro_detail) else ''
product_dim = pro_detail['产品尺寸'] if "Product Dimensions" in str(pro_detail) else ''
# 产品材料
try:
product_material = pro_detail['材料']
except:
product_material = ''
# 织物类型
try:
fabric_type = pro_detail['Fabric Type'] if "Fabric Type" in str(pro_detail) else " "
except:
fabric_type = ""
star_list = response.xpath('//table[@id="histogramTable"]//tr[@class="a-histogram-row a-align-center"]//td[3]//a/text()').extract()
if star_list:
try:
star_1 = star_list[0].strip()
except:
star_1 = 0
try:
star_2 = star_list[1].strip()
except:
star_2 = 0
try:
star_3 = star_list[2].strip()
except:
star_3 = 0
try:
star_4 = star_list[3].strip()
except:
star_4 = 0
try:
star_5 = star_list[4].strip()
except:
star_5 = 0
else:
star_1 = 0
星_2 = 0
星_3 = 0
星_4 = 0
星_5 = 0
如果 str(pro_detail) 中有 "首次可用日期",则
data_first_available = pro_detail['首次可用日期']。
if data_first_available:
data_first_available = datetime.datetime.strftime(
datetime.datetime.strptime(data_first_available, '%B %d, %Y'), '%Y/%m/%d')
否则:
data_first_available = ""
reviews_link = f'https://www.amazon.com/MIULEE-Decorative-Pillowcase-Cushion-Bedroom/product-reviews/{ASIN}/ref=cm_cr_arp_d_viewopt_fmt?ie=UTF8&reviewerType=all_reviews&formatType=current_format&pageNumber=1'
# 评论数、评分数
scrap_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
item['delivery']=delivery
item['seller']=seller
item['seller_link']= seller_link
item['brand_link']= brand_link
item['pic_link']=pic_link
item['title']= 标题
item['brand']=brand
item['star']=star
item['price']=price
item['color']=color
item['图案']=图案
item['材质']=材质
item['形状']=形状
item['five_points']=five_points
item['size_num']=size_num
item['color_num']=color_num
item['制造商']=制造商
item['item_weight']=item_weight
item['产品尺寸']=产品尺寸
item['产品材质']=产品材质
item['fabric_type']=fabric_type
item['star_1']=star_1
item['star_2']=star_2
item['star_3']=star_3
item['star_4']=star_4
item['star_5']=star_5
# item['ratings_num'] = ratings_num
# item['reviews_num'] = reviews_num
item['scrap_time']=scrap_time
item['reviews_link']=reviews_link
item['size']=size
item['data_first_available']=data_first_available
产生项目
收集大量数据时,应更改 IP 并处理验证码识别。
4. 下载中间件的方法
4.1 process_request(self, request, spider)
A.在每个请求通过下载中间件时调用。
B.返回 None:如果没有返回值(或明确返回 None),请求对象将被传递给下载器或其他权重较低的 process_request 方法。
C.返回响应对象:不再提出其他请求,并将响应返回给引擎。
D.返回请求对象:请求对象通过引擎传递给调度程序。其他权重较低的 process_request 方法会被跳过。
4.2 process_response(self, request, response, spider)
A.下载器完成 HTTP 请求并将响应传递给引擎时调用。
B.返回响应:传递给 spider 进行处理,或传递给其他下载中间件的 process_response 方法,权重较低。
C.返回请求对象:通过引擎传递给调度程序,以接收更多请求。其他权重较低的 process_request 方法会被跳过。
D.在 settings.py 中配置中间件激活并设置权重值。权重越低,优先级越高。
middlewares.py
4.3 设置代理 IP
类 ProxyMiddleware(对象):
def process_request(self,request, spider):
request.meta['proxy'] = proxyServer
request.header["Proxy-Authorization"] = proxyAuth
def process_response(self, request, response, spider):
if response.status != '200':
request.dont_filter = True
返回请求
class AmazonspiderDownloaderMiddleware:
# 并非所有方法都需要定义。如果没有定义方法、
# scrapy 的行为就好像下载器中间件没有修改
# 传递的对象。
@classmethod
def from_crawler(cls, crawler):
# Scrapy 使用此方法创建蜘蛛。
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
返回 s
def process_request(self, request, spider):
# USER_AGENTS_LIST: setting.py
user_agent = random.choice(USER_AGENTS_LIST)
request.headers['User-Agent'] = user_agent
cookies_str = "从浏览器粘贴的 cookie
# 将 cookie_str 传输到 cookie_dict
cookies_dict = {i[:i.find('=')]: i[i.find('=') + 1:] for i in cookies_str.split('; ')}
request.cookies = cookies_dict
# print("---------------------------------------------------")
# 打印(request.headers)
# print("---------------------------------------------------")
返回 None
def process_response(self, request, response, spider):
return response
def process_exception(self, request, exception, spider):
通过
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
4.5 获取 刮削 亚马逊的验证码,用于从亚马逊解锁。
def captcha_verfiy(img_name):
# captcha_verfiy
reader = easyocr.Reader(['ch_sim', 'en'])
# 阅读器 = easyocr.Reader(['en'], detection='DB', recognition = 'Transformer')
result = reader.readtext(img_name, detail=0)[0]
# result = reader.readtext('https://www.somewebsite.com/chinese_tra.jpg')
如果 result:
result = result.replace(' ', '')
返回结果
def download_captcha(captcha_url):
# 下载验证码
response = requests.get(captcha_url, stream=True)
try:
with open(r'./captcha.png', 'wb') as logFile:
for chunk in response:
logFile.write(chunk)
logFile.close()
print("Download done!")
except Exception as e:
print("Download log error!")
类 AmazonspiderVerifyMiddleware:
@classmethod
def from_crawler(cls, crawler):
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
返回 s
def process_request(self, request, spider):
返回 None
def process_response(self, request, response, spider):
# print(response.url)
if 'Captcha' in response.text:
headers = {
"user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
}
session = requests.session()
resp = session.get(url=response.url, headers=headers)
response1 = etree.HTML(resp.text)
captcha_url = "".join(response1.xpath('//div[@class="a-row a-text-center"]/img/@src'))
amzon = "".join(response1.xpath("//input[@name='amzn']/@value"))
amz_tr = "".join(response1.xpath("//input[@name='amzn-r']/@value"))
download_captcha(captcha_url)
captcha_text = captcha_verfiy('captcha.png')。
url_new = f "https://www.amazon.com/errors/validateCaptcha?amzn={amzon}&amzn-r={amz_tr}&field-keywords={captcha_text}"
resp = session.get(url=url_new, headers=headers)
if "对不起,我们需要确认您不是机器人" not in str(resp.text):
response2 = HtmlResponse(url=url_new, headers=headers,body=resp.text, encoding='utf-8')
if "对不起,我们需要确认您不是机器人" not in str(response2.text):
返回 response2
else:
返回请求
else:
return response
def process_exception(self, request, exception, spider):
通过
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
这就是有关亚马逊数据抓取的所有代码。
如需帮助,请联系 OkeyProxy 支持 知道。
推荐的代理供应商: Okeyproxy - 5 大 Socks5 代理服务器提供商,拥有来自 200 多个国家/地区的 150M+ 住宅代理服务器。 立即免费试用 1GB 住宅代理服务器!