Python实现爬取亚马逊数据并打印出Excel文件操作示例

#!/usr/bin/env python3
# encoding=UTF-8
import sys
import re
import urllib.request
import json
import time
import zlib
from html import unescape
import threading
import os
import xlwt
import math
import requests
#例如这里设置递归为一百万
sys.setrecursionlimit(1000000000)
##获取所有列别
def getProUrl():
  urlList = []
  headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36"}
  session = requests.Session()
  furl="https://www.amazon.cn/?tag=baidu250-23&hvadid={creative}&ref=pz_ic_22fvxh4dwf_e&page="
  for i in range(0,1):
    html=""
    html = session.post(furl+str(i),headers = headers)
    html.encoding = 'utf-8'
    s=html.text.encode('gb2312','ignore').decode('gb2312')
    url=r'</li><li id=".*?" data-asin="(.+?)" class="s-result-item celwidget">'
    reg=re.compile(url,re.M)
    name='"category" : "' + '(.*?)' + '"'
    reg1=re.compile(name,re.S)
    urlList = reg1.findall(html.text)
    return urlList
##根据类别获取数据链接
def getUrlData(ci):
   url="https://www.amazon.cn/s/ref=nb_sb_noss_2?__mk_zh_CN=%E4%BA%9A%E9%A9%AC%E9%80%8A%E7%BD%91%E7%AB%99&url=search-alias%3Daps&field-keywords="+ci+"&page=1&sort=review-rank"
   return url
##定时任务,等待1秒在进行
def fun_timer():
  time.sleep(3)
##根据链接进行查询每个类别的网页内容
def getProData(allUrlList):
  webContentHtmlList = []
  headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36"}
  for ci in allUrlList:
    session = requests.Session()
    fun_timer()
    html = session.get(getUrlData(ci),headers = headers)
    # 设置编码
    html.encoding = 'utf-8'
    html.text.encode('gb2312', 'ignore').decode('gb2312')
    gxg = r'</li><li id=".*?" data-asin="(.+?)" class="s-result-item celwidget">'
    reg = re.compile(gxg, re.M)
    items = reg.findall(html.text)
    print(html.text)
    webContentHtmlList.append(html.text)
  return webContentHtmlList
##根据网页内容过滤需要的属性和值
def getProValue():
  list1 = [] * 5
  list2 = [] * 5
  list3 = [] * 5
  list4 = [] * 5
  list5 = [] * 5
  list6 = [] * 5
  list7 = [] * 5
  list8 = [] * 5
  urlList = getProUrl();
  urlList.remove('全部分类')
  urlList.remove('Prime会员优先购')
  index = 0
  for head in urlList:
    if index >= 0 and index < 5:
      list1.append(head)
      index = index + 1
    if index >= 5 and index < 10:
      list2.append(head)
      index = index + 1
    if index >= 10 and index < 15:
      list3.append(head)
      index = index + 1
    if index >= 15 and index < 20:
      list4.append(head)
      index = index + 1
    if index >= 20 and index < 25:
      list5.append(head)
      index = index + 1
    if index >= 25 and index < 30:
      list6.append(head)
      index = index + 1
    if index >= 30 and index < 35:
      list7.append(head)
      index = index + 1
    if index >= 35 and index < 40:
      list8.append(head)
      index = index + 1
  webContentHtmlList1 = []
  webContentHtmlList1 = getProData(list1)
  webContentHtmlList2 = []
  webContentHtmlList2 = getProData(list2)
  webContentHtmlList3 = []
  webContentHtmlList3 = getProData(list3)
  webContentHtmlList4 = []
  webContentHtmlList4 = getProData(list4)
  webContentHtmlList5 = []
  webContentHtmlList5 = getProData(list5)
  webContentHtmlList6 = []
  webContentHtmlList6 = getProData(list6)
  webContentHtmlList7 = []
  webContentHtmlList7 = getProData(list7)
  webContentHtmlList8 = []
  webContentHtmlList8 = getProData(list8)
  ##存储所有数据的集合
  dataTwoAllList1 = []
  print("开始检索数据,检索数据中..........")
  ##网页内容1
  for html in webContentHtmlList1:
    for i in range(15):
      dataList = []
      dataList.append(unescape(getProCategory(html,i)))
      dataList.append(unescape(getProTitle(html,i)))
      dataList.append(getProPrice(html,i))
      dataList.append(getSellerCount(html,i))
      dataList.append(getProStar(html,i))
      dataList.append(getProCommentCount(html,i))
      print(dataList)
      dataTwoAllList1.append(dataList)
  ##网页内容2
  for html in webContentHtmlList2:
    for i in range(15):
      dataList = []
      dataList.append(unescape(getProCategory(html,i)))
      dataList.append(unescape(getProTitle(html,i)))
      dataList.append(getProPrice(html,i))
      dataList.append(getSellerCount(html,i))
      dataList.append(getProStar(html,i))
      dataList.append(getProCommentCount(html,i))
      print(dataList)
      dataTwoAllList1.append(dataList)
  ##网页内容3
  for html in webContentHtmlList3:
    for i in range(15):
      dataList = []
      dataList.append(unescape(getProCategory(html,i)))
      dataList.append(unescape(getProTitle(html,i)))
      dataList.append(getProPrice(html,i))
      dataList.append(getSellerCount(html,i))
      dataList.append(getProStar(html,i))
      dataList.append(getProCommentCount(html,i))
      print(dataList)
      dataTwoAllList1.append(dataList)
  ##网页内容4
  for html in webContentHtmlList4:
    for i in range(15):
      dataList = []
      dataList.append(unescape(getProCategory(html,i)))
      dataList.append(unescape(getProTitle(html,i)))
      dataList.append(getProPrice(html,i))
      dataList.append(getSellerCount(html,i))
      dataList.append(getProStar(html,i))
      dataList.append(getProCommentCount(html,i))
      print(dataList)
      dataTwoAllList1.append(dataList)
  ##网页内容5
  for html in webContentHtmlList5:
    for i in range(15):
      dataList = []
      dataList.append(unescape(getProCategory(html,i)))
      dataList.append(unescape(getProTitle(html,i)))
      dataList.append(getProPrice(html,i))
      dataList.append(getSellerCount(html,i))
      dataList.append(getProStar(html,i))
      dataList.append(getProCommentCount(html,i))
      print(dataList)
      dataTwoAllList1.append(dataList)
  ##网页内容6
  for html in webContentHtmlList6:
    for i in range(15):
      dataList = []
      dataList.append(unescape(getProCategory(html,i)))
      dataList.append(unescape(getProTitle(html,i)))
      dataList.append(getProPrice(html,i))
      dataList.append(getSellerCount(html,i))
      dataList.append(getProStar(html,i))
      dataList.append(getProCommentCount(html,i))
      print(dataList)
      dataTwoAllList1.append(dataList)
  ##网页内容7
  for html in webContentHtmlList7:
    for i in range(15):
      dataList = []
      dataList.append(unescape(getProCategory(html,i)))
      dataList.append(unescape(getProTitle(html,i)))
      dataList.append(getProPrice(html,i))
      dataList.append(getSellerCount(html,i))
      dataList.append(getProStar(html,i))
      dataList.append(getProCommentCount(html,i))
      print(dataList)
      dataTwoAllList1.append(dataList)
  ##网页内容8
  for html in webContentHtmlList8:
    for i in range(15):
      dataList = []
      dataList.append(unescape(getProCategory(html,i)))
      dataList.append(unescape(getProTitle(html,i)))
      dataList.append(getProPrice(html,i))
      dataList.append(getSellerCount(html,i))
      dataList.append(getProStar(html,i))
      dataList.append(getProCommentCount(html,i))
      print(dataList)
      dataTwoAllList1.append(dataList)
  print("检索数据完成！！！！")
  print("开始保存并打印Excel文档数据！！！！")
  ##保存文档
  createTable(time.strftime("%Y%m%d") + '亚马逊销量数据统计.xls', dataTwoAllList1)
##抽取类别
def getProCategory(html,i):
    i = 0;
    name = '<span class="a-color-state a-text-bold">' + '(.*?)' + '</span>'
    reg=re.compile(name,re.S)
    items = reg.findall(html)
    if len(items)==0:
      return ""
    else:
      if i<len(items):
        return items[i]
      else:
        return ""
##抽取标题
def getProTitle(html,i):
  html = getHtmlById(html,i)
  name = '<a class="a-link-normal s-access-detail-page s-color-twister-title-link a-text-normal" target="_blank" title="' + '(.*?)' + '"'
  reg=re.compile(name,re.S)
  items = reg.findall(html)
  if len(items)==0:
    return ""
  else:
    return items[0]
##抽取价格<a class="a-link-normal s-access-detail-page s-color-twister-title-link a-text-normal" target="_blank" title="
def getProPrice(html,i):
  html = getHtmlById(html,i)
  name = '<span class="a-size-base a-color-price s-price a-text-bold">' + '(.*?)' + '</span>'
  reg=re.compile(name,re.S)
  items = reg.findall(html)
  if len(items)==0:
    return "￥0"
  else:
    return items[0]
##抽取卖家统计
def getSellerCount(html,i):
  html = getHtmlById(html,i)
  name = '<span class="a-color-secondary">' + '(.*?)' + '</span>'
  reg=re.compile(name,re.S)
  items = reg.findall(html)
  if len(items)==0:
    return "(0 卖家)"
  else:
    return checkSellerCount(items,0)
##检查卖家统计
def checkSellerCount(items,i):
  result = items[i].find('卖家') >= 0
  if result:
    if len(items[i])<=9:
      return items[i]
    else:
      return '(0 卖家)'
  else:
    if i + 1 < len(items):
      i = i + 1
      result = items[i].find('卖家') >= 0
      if result:
        if len(items[i]) <= 9:
          return items[i]
        else:
          return '(0 卖家)'
        if i + 1 < len(items[i]):
          i = i + 1
          result = items[i].find('卖家') >= 0
          if result:
            if len(items[i]) <= 9:
              return items[i]
            else:
              return '(0 卖家)'
          else:
            return '(0 卖家)'
        else:
          return '(0 卖家)'
      else:
        return '(0 卖家)'
    else:
      return '(0 卖家)'
    return '(0 卖家)'
##抽取星级 <span class="a-icon-alt">
def getProStar(html,i):
  html = getHtmlById(html,i)
  name = '<span class="a-icon-alt">' + '(.*?)' + '</span>'
  reg=re.compile(name,re.S)
  items = reg.findall(html)
  if len(items)==0:
    return "平均 0 星"
  else:
    return checkProStar(items,0)
##检查星级
def checkProStar(items,i):
  result = items[i].find('星') >= 0
  if result:
      return items[i]
  else:
    if i + 1 < len(items):
      i = i + 1
      result = items[i].find('星') >= 0
      if result:
        return items[i]
      else:
        return '平均 0 星'
    else:
      return '平均 0 星'
    return '平均 0 星'
##抽取商品评论数量 销量
##<a class="a-size-small a-link-normal a-text-normal" target="_blank" href="https://www.amazon.cn/dp/B073LBRNV2/ref=sr_1_1?ie=UTF8&qid=1521782688&sr=8-1&keywords=%E5%9B%BE%E4%B9%A6#customerReviews" rel="external nofollow" >56</a>
def getProCommentCount(html,i):
  name = '<a class="a-size-small a-link-normal a-text-normal" target="_blank" href=".*?#customerReviews" rel="external nofollow" ' + '(.*?)' + '</a>'
  reg=re.compile(name,re.S)
  items = reg.findall(html)
  if len(items)==0:
    return "0"
  else:
    if i<len(items):
      return items[i].strip(">")
    else:
      return "0"
##根据id取出html里面的内容
def get_id_tag(content, id_name):
 id_name = id_name.strip()
 patt_id_tag = """<[^>]*id=['"]?""" + id_name + """['" ][^>]*>"""
 id_tag = re.findall(patt_id_tag, content, re.DOTALL|re.IGNORECASE)
 if id_tag:
   id_tag = id_tag[0]
 else:
   id_tag=""
 return id_tag
##缩小范围 定位值
def getHtmlById(html,i):
    start = get_id_tag(html,"result_"+str(i))
    i=i+1
    end = get_id_tag(html, "result_" + str(i))
    name = start + '.*?'+end
    reg = re.compile(name, re.S)
    html = html.strip()
    items = reg.findall(html)
    if len(items) == 0:
      return ""
    else:
      return items[0]
##生成word文档
def createTable(tableName,dataTwoAllList):
  flag = 1
  results = []
  results.append("类别,标题,价格,卖家统计,星级,评论数")
  columnName = results[0].split(',')
  # 创建一个excel工作簿，编码utf-8，表格中支持中文
  wb = xlwt.Workbook(encoding='utf-8')
  # 创建一个sheet
  sheet = wb.add_sheet('sheet 1')
  # 获取行数
  rows = math.ceil(len(dataTwoAllList))
  # 获取列数
  columns = len(columnName)
  # 创建格式style
  style = xlwt.XFStyle()
  # 创建font，设置字体
  font = xlwt.Font()
  # 字体格式
  font.name = 'Times New Roman'
  # 将字体font，应用到格式style
  style.font = font
  # 创建alignment，居中
  alignment = xlwt.Alignment()
  # 居中
  alignment.horz = xlwt.Alignment.HORZ_CENTER
  # 应用到格式style
  style.alignment = alignment
  style1 = xlwt.XFStyle()
  font1 = xlwt.Font()
  font1.name = 'Times New Roman'
  # 字体颜色（绿色）
  # font1.colour_index = 3
  # 字体加粗
  font1.bold = True
  style1.font = font1
  style1.alignment = alignment
  for i in range(columns):
    # 设置列的宽度
    sheet.col(i).width = 5000
  # 插入列名
  for i in range(columns):
    sheet.write(0, i, columnName[i], style1)
  for i in range(1,rows):
    for j in range(0,columns):
      sheet.write(i, j, dataTwoAllList[i-1][j], style)
    wb.save(tableName)
##入口开始
input("按回车键开始导出..........")
fun_timer()
print("三秒后开始抓取数据.......,请等待！")
getProValue();
print("数据导出成功!请注意查看!")
print("数据文档《亚马逊销量数据统计.xls》已经存于C盘下面的C:\Windows\SysWOW64的该路径下面！！！！")
input()