python获取淘宝指定商品的评论信息（需提前获取商品的详细信息的url地址）

参考：https://blog.csdn.net/qq_32670879/article/details/81903101

 废话不多说直接上代码。

获取商品的详细信息url可以参考博客：https://blog.csdn.net/qq_32670879/article/details/81903101

#encoding=utf-8
# Created by double lin at 2018/8/21

import requests
import re
import json

def get_comments(lastPage, url):

    comments = []

    for page in range(1, lastPage + 1):
        comments_url = url.format(page)
        r = requests.get(comments_url)
        content = json.loads(re.findall(r'\{.+?\}\}', r.text)[0])
        for item in content['rateDetail']['rateList']:
            pics = []
            for i in range(len(item['pics'])):
                pics.append(item['pics'][i])
            temp = {
                "rateDate": item['rateDate'],
                "rateContent": item['rateContent'],
                "sellerId": item['sellerId'],
                "id": item['id'],
                'pics': pics,
            }
            comments.append(temp)

    print len(comments)

    for i in range(len(comments)):
        rateContent = comments[i]['rateContent']
        for j in range(len(comments[i]['pics'])):
            print comments[i]['pics'][j]
        print rateContent


if __name__ == "__main__":

    page = 1
    url =   'https://rate.tmall.com/list_detail_rate.htm?itemId=571214463078&spuId=973961177&sellerId=2548289425&order=3' \
            '&currentPage={}&append=0&content=1&tagId=&posi=&picture=&ua=098%23E1hv9vvbvnpvUvCkvvvvvjiPPsF9ljtRRLzv6jthPm' \
            'PUtji8PLdytjnjPF5pQjiU9phv2HiwjSaSzHi479UgzgwCvvpv9hCvRphvCvvvphvEvpCWv9t%2FN3zxRLwp%2B3%2Bulj7JeC4AVAdWaXT' \
            'AdX9aB%2BBlHd8rejOdYWpfDf8rwZEl%2Bb8reEyaUExreEAKjkx%2F1nkKHd8rwZalYEmAdX3sbdyCvm9vvhCvvvvvvvvvBGwvvvC5vvCj' \
            '1Qvvv3QvvhNjvvvmmvvvBGwvvvUUkphvC9hvpyPOl8yCvv9vvhhywN7qhQhCvvOvChCvvvvPvpvhvv2MMTwCvvpvvhHhRphvCvvvphv%3D&' \
            'needFold=0&_ksTS=1534855094470_928&callback=jsonp929'
    #详细评价信息
    comments_url = url.format(page)

    comments = []
    r = requests.get(comments_url)
    print r.text
    content = re.findall(r'\{.+?\}\}', r.text)[0]
    content = json.loads(content)
    lastPage = content['rateDetail']['paginator']['lastPage']

    get_comments(lastPage, url)