前言
什么样的面包品牌最好卖？什么样的口感最受欢迎？相信每一位喜欢面包的朋友都会关心这些问题。本文通过爬取京东面包类数据，一方面回答大家关于此前关于面包的各种问题，另一方面也带大家了解一份完整的数据报告，可以从中有所借鉴。
数据爬取（部分代码）
构建解析详情页的代理
def disguiser():
'''
构建解析详情页的代理
'''
try:
req = request.Request('http://www.agent.cn/xdaili-api//greatRecharge/getGreatIp?spiderId=8f75fb741de34cfb95adf347910db7a9&orderno=YZ20191169208Yi1jmu&returnType=2&count=1')
resp = request.urlopen(req)
jsonIP = resp.read().decode()
jsonIP = re.sub(' ','',jsonIP)
ipList = re.findall('"ip":"(.*?)"',jsonIP)
portList = re.findall('"port":"(.*?)"',jsonIP)
value = list(map(lambda x,y : x + ':' + y,ipList, portList))
key = ['http']
ipDict = {key[index] : value[index] for index in range(len(key))}
print(ipDict)
# 1. 使用ProxyHandler，传入代理构建一个handler
handler = request.ProxyHandler(ipDict) # key: http/https val: ip:port
# 2. 使用上面创建的handler构建一个opener
opener = request.build_opener(handler)
print(opener)
except:
time.sleep(6)
req = request.Request('http://www.agent.cn/xdaili-api//greatRecharge/getGreatIp?spiderId=8f75fb741de34cfb95adf347910db7a9&orderno=YZ20191169208Yi1jmu&returnType=2&count=1')
resp = request.urlopen(req)
jsonIP = resp.read().decode()
jsonIP = re.sub(' ','',jsonIP)
ipList = re.findall('"ip":"(.*?)"',jsonIP)
portList = re.findall('"port":"(.*?)"',jsonIP)
value = list(map(lambda x,y : x + ':' + y,ipList, portList))
key = ['http']
ipDict = {key[index] : value[index] for index in range(len(key))}
print(ipDict)
# 1. 使用ProxyHandler，传入代理构建一个handler
handler = request.ProxyHandler(ipDict) # key: http/https val: ip:port
# 2. 使用上面创建的handler构建一个opener
opener = request.build_opener(handler)
return opener解析详情页的内容
def parser(pageQueue, uaPool, priceRequestDoc, PRICEBASEURL, detailRequestDoc, open):
'''
解析详情页的内容
'''
detailUrl = pageQueue.get()[1]
print(detailUrl)
# 价格
PRICEURL = PRICEBASEURL + re.search('\d+',detailUrl).group()
priceRequestDoc = re.sub(r' ','',priceRequestDoc)
headers_for_price = dict(re.findall('([-\w\d]*?):(.*)',priceRequestDoc))
headers_for_price.update(uaPool[random.randint(0,len(uaPool)-1)]) # 获取商品价格信息请求的headers信息
req = request.Request(PRICEURL, headers = headers_for_price)
resp = open(req) #第一次响应
print(PRICEURL,'商品价格页请求响应码：',resp.getcode())
if resp.getcode() == 200:
info = resp.read().decode()
elif SERVER_ERROR_MIN <= response.status_code < SERVER_ERROR_MAX:
for i in range(5):
time.sleep(i**i) #可以继续优化,第一次1秒,第二次10秒,第三次100秒...
resp = open(req)
if resp.getcode() == 200:
break
elif SERVER_ERROR_MIN <= response.status_code < SERVER_ERROR_MAX:
if response.status_code == 404:
print('page not found')
elif response.status_code == 403:
print('have no right')
else:
pass
info = json.loads(info)
item_price = info[0]['p']
# 名称 品牌 是否含糖 保质期 配料 包装 商品产地...
detailRequestDoc = re.sub(r' ','',detailRequestDoc)
headers_for_detail = dict(re.findall('([-\w\d:]*):(.*)',detailRequestDoc))
headers_for_detail.update(uaPool[random.randint(0,9)]) # 获取商品价格信息请求的headers信息
req = request.Request(detailUrl, headers = headers_for_detail)
resp = open(req) # 第二个响应
print(detailUrl,'详情页请求响应：',resp.getcode())
if resp.getcode() == 200:
pass
elif SERVER_ERROR_MIN <= response.status_code < SERVER_ERROR_MAX:
for i in range(5):
time.sleep(i**i) #可以继续优化,第一次1秒,第二次10秒,第三次100秒...
resp = open(req)
if resp.getcode() == 200:
break
elif SERVER_ERROR_MIN <= response.status_code < SERVER_ERROR_MAX:
if response.status_code == 404:
print(detailUrl,'page not found')
elif response.status_code == 403:
print(detailUrl,'have no right')
else:
pass
parser = etree.HTMLParser(encoding = 'gbk')
html = etree.parse(resp, parser = parser)
print(html)
elements = html.xpath("//ul[@class='parameter2 p-parameter-list']//text() | //dl[@class='clearfix']//text()")
detailInfo = list(filter(lambda msg : len(msg.strip()) > 0 and msg, elements))
detailInfo = ('#').join(detailInfo)
try:
item_name = re.search('商品名称：(.*?)#',detailInfo).group(1)
except AttributeError:
# print('商品没有 item_name 信息')
item_name = 'n'
try:
item_id = re.search('\d+',detailUrl).group()
except AttributeError:
# print('商品没有 item_id 信息')
item_id = 'n'
# 大商品名称
elementTitle = html.xpath("//title//text()")[0]
elementTitle = elementTitle.strip()
item_fullName = re.search('(【.*】)*(.*)?【',elementTitle).group(2)
# 品牌
elementBrand = html.xpath("//*[@id='crumb-wrap']/div/div[1]/div[7]/div/div/div[1]/a/text()")
elementBrand = list(filter(lambda msg : len(msg.strip()) > 0 and msg, elementBrand))
try:
item_brand = elementBrand[0]
except IndexError:
item_brand = 'npl'
yield {
'item_id':item_id,
'item_fullName':item_fullName,
'item_name':item_name,
'item_price':item_price,
'item_brand':item_brand,
'gross_weight':gross_weight,
'item_origin':item_origin,
'item_certification':item_certification,
'processing_technology':processing_technology,
'packing_unit':packing_unit,
'is_suger':is_suger
}由于公众号篇幅有限，无法展示本文全部代码，我们已将代码放入百度云盘。后台回复“面包”，可以获取本文代码。
分析正文
