python爬虫亚马逊评论_亚马逊差爬虫+差评提醒+评论抓取

# -*- coding:utf-8 -*-

import urllib,urllib2,re

from lxml import etree

import requests

import random

import json

import conf

import time,datetime

import os,sys

sys.path.append('./')

def randHeader():

head_connection = ['Keep-Alive', 'close']

head_accept = ['text/html, application/xhtml+xml, */*']

head_accept_language = ['zh-CN,fr-FR;q=0.5', 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3']

head_user_agent = ['Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko',

'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36',

'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)',

'Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1',

'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3',

'Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12',

'Opera/9.27 (Windows NT 5.2; U; zh-cn)',

'Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0',

'Opera/8.0 (Macintosh; PPC Mac OS X; U; en)',

'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6',

'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)',

'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)',

'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)',

'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ',

'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)',

'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ',

'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER',

'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)',

'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11']

header = {

'Connection': head_connection[0],

'Accept': head_accept[0],

'Accept-Language': head_accept_language[1],

'User-Agent': head_user_agent[random.randrange(0, len(head_user_agent))]

}

return header

def getUrl(goods,star):

url = "https://www.amazon.com/hz/reviews-render/ajax/reviews/get/ref=cm_cr_arp_d_viewopt_sr?sortBy=recent&reviewerType=all_reviews&formatType=&mediaType=&filterByStar="+star+"&pageNumber=1&filterByKeyword=&shouldAppend=undefined&deviceType=desktop&reftag=cm_cr_arp_d_viewopt_srt&pageSize=10&asin=" + goods

return url

def getText(url):

head_dict = randHeader()

r = requests.get(url,headers = head_dict)

content = r.text

return content

if __name__ == '__main__':

dt = datetime.datetime.now().strftime("%Y-%m-%d%H:%M:%S")

#url = "https://www.amazon.com/hz/reviews-render/ajax/reviews/get/ref=cm_cr_arp_d_viewopt_sr?sortBy=recent&reviewerType=all_reviews&formatType=&mediaType=&filterByStar=one_star&pageNumber=1&filterByKeyword=&shouldAppend=undefined&deviceType=desktop&reftag=cm_cr_arp_d_viewopt_srt&pageSize=10&asin=" + goods

goods_dict = conf.goods_dict

for goods in goods_dict.keys():

for star in ['all_stars']:

url = getUrl(goods, star)

page = getText(url)

if len(page.split('&&&')) > 5:

all_num = int(etree.HTML(json.loads(page.split('&&&')[1])[2]).xpath('//*[@class="a-size-base"]')[0].text.split(' ')[3].replace(',',''))

file_path = star +"/"+ goods

content = 0

num = 0

if os.path.exists(file_path):

with open(file_path, 'r') as f:

content = int(f.read())

if all_num > content:

num = all_num - content

if num > 0:

for i in range(4, 4 + num):

star_num = int(float(etree.HTML(json.loads(page.split('&&&')[i])[2]).xpath('//*[@class="a-icon-alt"]')[0].text.split(' ')[0]))

if star_num < 4:

send_message = goods_dict[goods] + ':新增加一条'+str(star_num)+'星评论'

cmd = 'sh my_email.sh "' + send_message + '"'

os.system(cmd)

with open(file_path, 'w+') as f:

f.write(str(all_num))

else:

with open(file_path, 'w+') as f:

f.write(str(all_num))

else:

with open(file_path, 'w+') as f:

f.write(str(all_num))