【函数式】爬取京东评论及型号【智能判断总评论页数】

import requests
import pandas as pd
import json
from lxml import etree
import time

c_num = input(r"请输入要下载评论的商品编号：")

def d_cont(c_num,num):
    url =f"https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId={c_num}&score=0&sortType=5&page={int(num)}&pageSize=10&isShadowSku=0&rid=0&fold=1"
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.36'}
    response = requests.get(url=url,headers=headers,timeout=5).text   
    response = response.replace("fetchJSON_comment98(","")   
    response = response.replace(');','')
    dt = json.loads(response)    
    c_cont = dt['productCommentSummary']['commentCount']
    num1 = c_cont/10 if c_cont%10 == 0 else c_cont//10 + c_cont%10   
    return num1,dt

def download_cont(c_num,num1):
    for i in range(num1):
        d_cont(c_num,i)       
        dt_list = dt['comments']       
        cont = [i["content"] for i in dt_list]
        color = [j["productColor"] for j in dt_list]
        size = [b["productSize"] for b in dt_list]
        date = pd.DataFrame({"评价":cont,"颜色":color,"型号":size},)
        date.index = date.index + 1
        date.to_csv("e:/京东评论.csv",mode = "a",header=0,encoding = "ANSI")
        j = 1
        print(f"第{j}页下载完成")
        j += 1
        time.sleep(3)

num1,dt = d_cont(c_num,0)
download_cont(c_num,num1)

import requests
import pandas as pd
import json
from lxml import etree
import time

c_num = input(r"请输入要下载评论的商品编号：")
def d_cont(c_num,num):
    url =f"https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId={c_num}&score=0&sortType=5&page={int(num)}&pageSize=10&isShadowSku=0&rid=0&fold=1"
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.36'}
    response = requests.get(url=url,headers=headers,timeout=5).text   
    response = response.replace("fetchJSON_comment98(","")   
    response = response.replace(');','')
    dt = json.loads(response)    
    c_cont = dt['productCommentSummary']['commentCount']
    num1 = c_cont/10 if c_cont%10 == 0 else c_cont//10 + c_cont%10   
    return num1,dt

def download_cont(c_num,num1):
    for i in range(num1):
        d_cont(c_num,i)       
        dt_list = dt['comments']       
        cont = [i["content"] for i in dt_list]
        color = [j["productColor"] for j in dt_list]
        size = [b["productSize"] for b in dt_list]
        date = pd.DataFrame({"评价":cont,"颜色":color,"型号":size},)
        date.index = date.index + 1
        date.to_csv("e:/京东评论.csv",mode = "a",header=0,encoding = "ANSI")
        j = 1
        print(f"第{j}页下载完成")
        j += 1
        time.sleep(3)

num1,dt = d_cont(c_num,0)
download_cont(c_num,num1)