Python如何获取亚马逊的评论信息并进行处理
本篇内容主要讲解"Python如何获取亚马逊的评论信息并进行处理",感兴趣的朋友不妨来看看。本文介绍的方法操作简单快捷,实用性强。下面就让小编来带大家学习"Python如何获取亚马逊的评论信息并进行处理"吧!
一、分析亚马逊的评论请求
首先打开开发者模式的Network,Clear清屏做一次请求:
你会发现在Doc中的get请求正好就有我们想要的评论信息。
可是真正的评论数据可不是全部都在这里的,页面往下翻,有个翻页的button:
点击翻页请求下一页,在Fetch/XHR选项卡中多了一个新的请求,刚才的Doc选项卡中并无新的get请求。这下发现了所有的评论信息是XHR类型的请求。
获取到post请求的链接和payload数据,里面含有控制翻页的参数,真正的评论请求已经找到了。
这一堆就是未处理的信息,这些请求未处理的信息里面,带有data-hook=\"review\"的就是带有评论的信息。分析完毕,下面开始一步一步去写请求。
二、获取亚马逊评论的内容
首先拼凑请求所需的post参数,请求链接,以便之后的自动翻页,然后带参数post请求链接:
headers = { 'authority': 'www.amazon.it', "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9", "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36",} page = 1post_data = { "sortBy": "recent", "reviewerType": "all_reviews", "formatType": "", "mediaType": "", "filterByStar": "", "filterByLanguage": "", "filterByKeyword": "", "shouldAppend": "undefined", "deviceType": "desktop", "canShowIntHeader": "undefined", "pageSize": "10", "asin": "B08GHGTGQ2",}# 翻页关键payload参数赋值post_data["pageNumber"] = page,post_data["reftag"] = f"cm_cr_getr_d_paging_btm_next_{page}",post_data["scope"] = f"reviewsAjax{page}",# 翻页链接赋值spiderurl=f'https://www.amazon.it/hz/reviewsrender/ajax/reviews/get/ref=cm_cr_getr_d_paging_btm_next_{page}'res = requests.post(spiderurl,headers=headers,data=post_data)if res and res.status_code == 200: res = res.content.decode('utf-8') print(res)
现在已经获取到了这一堆未处理的信息,接下来开始对这些数据进行处理。
三、亚马逊评论信息的处理
上图的信息会发现,每一段的信息都由"&&&"进行分隔,而分隔之后的每一条信息都是由'","'分隔开的:
所以用python的split方法进行处理,把字符串分隔成list列表:
# 返回值字符串处理contents = res.split('&&&')for content in contents: infos = content.split('","')
由'","'分隔的数据通过split处理生成新的list列表,评论内容是列表的最后一个元素,去掉里面的"\","\n"和多余的符号,就可以通过css/xpath选择其进行处理了:
for content in contents: infos = content.split('","') info = infos[-1].replace('"]','').replace('\\n','').replace('\\','') # 评论内容判断 if 'data-hook="review"' in info: sel = Selector(text=info) data = {} data['username'] = sel.xpath('//span[@class="a-profile-name"]/text()').extract_first() #用户名 data['point'] = sel.xpath('//span[@class="a-icon-alt"]/text()').extract_first() #评分 data['date'] = sel.xpath('//span[@data-hook="review-date"]/text()').extract_first() #日期地址 data['review'] = sel.xpath('//span[@data-hook="review-title"]/span/text()').extract_first() #评价标题 data['detail'] = sel.xpath('//span[@data-hook="review-body"]').extract_first() #评价内容 image = sel.xpath('div[@class="review-image-tile-section"]').extract_first() data['image'] = image if image else "not image" #图片 print(data)
四、代码整合
4.1 代理设置
稳定的IP代理是你数据获取最有力的工具。目前国内还是无法稳定的访问亚马逊,会出现连接失败的情况。我这里使用的ipidea代理请求的意大利地区的亚马逊,可以通过账密和api获取代理,速度还是非常稳定的。
地址:http://www.ipidea.net/?utm-source=csdn&utm-keyword=?wb
下面的代理获取的方法:
# api获取ip def getApiIp(self): # 获取且仅获取一个ip------意大利 api_url = '获取代理地址' res = requests.get(api_url, timeout=5) try: if res.status_code == 200: api_data = res.json()['data'][0] proxies = { 'http': 'http://{}:{}'.format(api_data['ip'], api_data['port']), 'https': 'http://{}:{}'.format(api_data['ip'], api_data['port']), } print(proxies) return proxies else: print('获取失败') except: print('获取失败')
4.2 while循环翻页
while循环进行翻页,评论最大页数是99页,99页之后就break跳出while循环:
def getPLPage(self): while True: # 翻页关键payload参数赋值 self.post_data["pageNumber"]= self.page, self.post_data["reftag"] = f"cm_cr_getr_d_paging_btm_next_{self.page}", self.post_data["scope"] = f"reviewsAjax{self.page}", # 翻页链接赋值 spiderurl = f'https://www.amazon.it/hz/reviews-render/ajax/reviews/get/ref=cm_cr_getr_d_paging_btm_next_{self.page}' res = self.getRes(spiderurl,self.headers,'',self.post_data,'POST',check)#自己封装的请求方法 if res: res = res.content.decode('utf-8') # 返回值字符串处理 contents = res.split('&&&') for content in contents: infos = content.split('","') info = infos[-1].replace('"]','').replace('\\n','').replace('\\','') # 评论内容判断 if 'data-hook="review"' in info: sel = Selector(text=info) data = {} data['username'] = sel.xpath('//span[@class="a-profile-name"]/text()').extract_first() #用户名 data['point'] = sel.xpath('//span[@class="a-icon-alt"]/text()').extract_first() #评分 data['date'] = sel.xpath('//span[@data-hook="review-date"]/text()').extract_first() #日期地址 data['review'] = sel.xpath('//span[@data-hook="review-title"]/span/text()').extract_first() #评价标题 data['detail'] = sel.xpath('//span[@data-hook="review-body"]').extract_first() #评价内容 image = sel.xpath('div[@class="review-image-tile-section"]').extract_first() data['image'] = image if image else "not image" #图片 print(data) if self.page <= 99: print('Next Page') self.page += 1 else: break
最后的整合代码:
# coding=utf-8import requestsfrom scrapy import Selector class getReview(): page = 1 headers = { 'authority': 'www.amazon.it', "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9", "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36", } post_data = { "sortBy": "recent", "reviewerType": "all_reviews", "formatType": "", "mediaType": "", "filterByStar": "", "filterByLanguage": "", "filterByKeyword": "", "shouldAppend": "undefined", "deviceType": "desktop", "canShowIntHeader": "undefined", "pageSize": "10", "asin": "B08GHGTGQ2", #post_data中asin参数目前写死在 #"https://www.amazon.it/product-reviews/B08GHGTGQ2?ie=UTF8&pageNumber=1&reviewerType=all_reviews&pageSize=10&sortBy=recent" #这个链接里,不排除asin值变化的可能,如要获取get请求即可 def getPLPage(self): while True: # 翻页关键payload参数赋值 self.post_data["pageNumber"]= self.page, self.post_data["reftag"] = f"cm_cr_getr_d_paging_btm_next_{self.page}", self.post_data["scope"] = f"reviewsAjax{self.page}", # 翻页链接赋值 spiderurl = f'https://www.amazon.it/hz/reviews-render/ajax/reviews/get/ref=cm_cr_getr_d_paging_btm_next_{self.page}' res = self.getRes(spiderurl,self.headers,'',self.post_data,'POST',check)#自己封装的请求方法 if res: res = res.content.decode('utf-8') # 返回值字符串处理 contents = res.split('&&&') for content in contents: infos = content.split('","') info = infos[-1].replace('"]','').replace('\\n','').replace('\\','') # 评论内容判断 if 'data-hook="review"' in info: sel = Selector(text=info) data = {} data['username'] = sel.xpath('//span[@class="a-profile-name"]/text()').extract_first() #用户名 data['point'] = sel.xpath('//span[@class="a-icon-alt"]/text()').extract_first() #评分 data['date'] = sel.xpath('//span[@data-hook="review-date"]/text()').extract_first() #日期地址 data['review'] = sel.xpath('//span[@data-hook="review-title"]/span/text()').extract_first() #评价标题 data['detail'] = sel.xpath('//span[@data-hook="review-body"]').extract_first() #评价内容 image = sel.xpath('div[@class="review-image-tile-section"]').extract_first() data['image'] = image if image else "not image" #图片 print(data) if self.page <= 99: print('Next Page') self.page += 1 else: break # api获取ip def getApiIp(self): # 获取且仅获取一个ip------意大利 api_url = '获取代理地址' res = requests.get(api_url, timeout=5) try: if res.status_code == 200: api_data = res.json()['data'][0] proxies = { 'http': 'http://{}:{}'.format(api_data['ip'], api_data['port']), 'https': 'http://{}:{}'.format(api_data['ip'], api_data['port']), } print(proxies) return proxies print('获取失败') except: print('获取失败') #专门发送请求的方法,代理请求三次,三次失败返回错误 def getRes(self,url,headers,proxies,post_data,method): if proxies: for i in range(3): try: # 传代理的post请求 if method == 'POST': res = requests.post(url,headers=headers,data=post_data,proxies=proxies) # 传代理的get请求 else: res = requests.get(url, headers=headers,proxies=proxies) if res: return res except: print(f'第{i+1}次请求出错') else: return None else: proxies = self.getApiIp() # 请求代理的post请求 res = requests.post(url, headers=headers, data=post_data, proxies=proxies) # 请求代理的get请求 res = requests.get(url, headers=headers, proxies=proxies) print(f"第{i+1}次请求出错")if __name__ == '__main__': getReview().getPLPage()
到此,相信大家对"Python如何获取亚马逊的评论信息并进行处理"有了更深的了解,不妨来实际操作一番吧!这里是网站,更多相关内容可以进入相关频道进行查询,关注我们,继续学习!