本文實例講述了Python實現爬取亞馬遜數據并打印出Excel文件操作。分享給大家供大家參考,具體如下:
python大神們別噴,代碼寫的很粗糙,主要是完成功能,能夠借鑒就看下吧,我是學java的,畢竟不是學python的,自己自學看了一點點python,望諒解。
#!/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
#例如這里設置遞歸為一百萬
sys.setrecursionlimit(1000000000)
##獲取所有列別
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'
'
reg=re.compile(url,re.M)
name='"category" : "' + '(.*?)' + '"'
reg1=re.compile(name,re.S)
urlList = reg1.findall(html.text)
return urlList
##根據類別獲取數據鏈接
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
##定時任務,等待1秒在進行
def fun_timer():
time.sleep(3)
##根據鏈接進行查詢每個類別的網頁內容
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)
# 設置編碼
html.encoding = 'utf-8'
html.text.encode('gb2312', 'ignore').decode('gb2312')
gxg = r'
'
reg = re.compile(gxg, re.M)
items = reg.findall(html.text)
print(html.text)
webContentHtmlList.append(html.text)
return webContentHtmlList
##根據網頁內容過濾需要的屬性和值
def getProValue():
list1 = [] * 5
list2 = [] * 5
list3 = [] * 5
list4 = [] * 5
list5 = [] * 5
list6 = [] * 5
list7 = [] * 5
list8 = [] * 5
urlList = getProUrl();
urlList.remove('全部分類')
urlList.remove('Prime會員優先購')
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)
##存儲所有數據的集合
dataTwoAllList1 = []
print("開始檢索數據,檢索數據中..........")
##網頁內容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)
##網頁內容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)
##網頁內容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)
##網頁內容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)
##網頁內容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)
##網頁內容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)
##網頁內容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)
##網頁內容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("檢索數據完成!!!!")
print("開始保存并打印Excel文檔數據!!!!")
##保存文檔
createTable(time.strftime("%Y%m%d") + '亞馬遜銷量數據統計.xls', dataTwoAllList1)
##抽取類別
def getProCategory(html,i):
i = 0;
name = '
' + '(.*?)' + '
'
reg=re.compile(name,re.S)
items = reg.findall(html)
if len(items)==0:
return ""
else:
if i
' + '(.*?)' + ''
reg=re.compile(name,re.S)
items = reg.findall(html)
if len(items)==0:
return "¥0"
else:
return items[0]
##抽取賣家統計
def getSellerCount(html,i):
html = getHtmlById(html,i)
name = '
' + '(.*?)' + '
'
reg=re.compile(name,re.S)
items = reg.findall(html)
if len(items)==0:
return "(0 賣家)"
else:
return checkSellerCount(items,0)
##檢查賣家統計
def checkSellerCount(items,i):
result = items[i].find('賣家') >= 0
if result:
if len(items[i])<=9:
return items[i]
else:
return '(0 賣家)'
else:
if i + 1 < len(items):
i = i + 1
result = items[i].find('賣家') >= 0
if result:
if len(items[i]) <= 9:
return items[i]
else:
return '(0 賣家)'
if i + 1 < len(items[i]):
i = i + 1
result = items[i].find('賣家') >= 0
if result:
if len(items[i]) <= 9:
return items[i]
else:
return '(0 賣家)'
else:
return '(0 賣家)'
else:
return '(0 賣家)'
else:
return '(0 賣家)'
else:
return '(0 賣家)'
return '(0 賣家)'
##抽取星級
def getProStar(html,i):
html = getHtmlById(html,i)
name = '
' + '(.*?)' + '
'
reg=re.compile(name,re.S)
items = reg.findall(html)
if len(items)==0:
return "平均 0 星"
else:
return checkProStar(items,0)
##檢查星級
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'
##抽取商品評論數量 銷量
##
56
def getProCommentCount(html,i):
name = '
'
reg=re.compile(name,re.S)
items = reg.findall(html)
if len(items)==0:
return "0"
else:
if i
")
else:
return "0"
##根據id取出html里面的內容
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
##縮小范圍 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文檔
def createTable(tableName,dataTwoAllList):
flag = 1
results = []
results.append("類別,標題,價格,賣家統計,星級,評論數")
columnName = results[0].split(',')
# 創建一個excel工作簿,編碼utf-8,表格中支持中文
wb = xlwt.Workbook(encoding='utf-8')
# 創建一個sheet
sheet = wb.add_sheet('sheet 1')
# 獲取行數
rows = math.ceil(len(dataTwoAllList))
# 獲取列數
columns = len(columnName)
# 創建格式style
style = xlwt.XFStyle()
# 創建font,設置字體
font = xlwt.Font()
# 字體格式
font.name = 'Times New Roman'
# 將字體font,應用到格式style
style.font = font
# 創建alignment,居中
alignment = xlwt.Alignment()
# 居中
alignment.horz = xlwt.Alignment.HORZ_CENTER
# 應用到格式style
style.alignment = alignment
style1 = xlwt.XFStyle()
font1 = xlwt.Font()
font1.name = 'Times New Roman'
# 字體顏色(綠色)
# font1.colour_index = 3
# 字體加粗
font1.bold = True
style1.font = font1
style1.alignment = alignment
for i in range(columns):
# 設置列的寬度
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)
##入口開始
input("按回車鍵開始導出..........")
fun_timer()
print("三秒后開始抓取數據.......,請等待!")
getProValue();
print("數據導出成功!請注意查看!")
print("數據文檔《亞馬遜銷量數據統計.xls》已經存于C盤下面的C:\Windows\SysWOW64的該路徑下面!!!!")
input()
結果數據:
打包成exe文件,直接可以點擊運行:打包過程我就不一一說了,都是一些命令操作:
要安裝pyinstaller,打成exe的操作命令:--inco是圖標,路徑和項目當前路徑一樣
途中遇到很多問題,都一一解決了,亂碼,ip限制,打包后引入模塊找不到,遞歸最大次數,過濾的一些問題
pyinstaller -F -c --icon=my.ico crawling.py
??? 這是打包命令
效果圖:
更多關于Python相關內容可查看本站專題:《Python Socket編程技巧總結》、《Python正則表達式用法總結》、《Python數據結構與算法教程》、《Python函數使用技巧總結》、《Python字符串操作技巧匯總》、《Python入門與進階經典教程》及《Python文件與目錄操作技巧匯總》
希望本文所述對大家Python程序設計有所幫助。