第一步:
准备数据:http+heads
第二步:
发送请求:
repnose = requests.get(url,headers=self.headers)
第三步:
数据解析:使用xpath对html数据进行解析
# 数据分组
div_list = html.xpath("//div[@class='as-macbtr-optioncontent']")
content_list = []
for div in div_list:
item = {}
# 获取字段值
item["month"] = div.xpath(".//div[@class='as-price']/span[@class='as-price-installments']/a/text()")
item["month"] = item["month"][0][:1] if len(item["month"]) > 0 else None
item["content"] = div.xpath(".//h3[@class='as-macbundle-modelvariationtitle']/text()")
item["content"] = item["content"] if len(item["content"]) > 0 else None
print(item)
content_list.append(item)
第四步:
保存数据到本地
with open("apple.txt", "a", encoding="utf-8") as f:
for content in content_list:
f.write(json.dumps(content, ensure_ascii=False, indent=2))
f.write("\n")
爬取效果: