点击评论,刷出这个带评论的包。
page=0是页数,通过控制page来控制翻页。
请求头参考!(可复制)
import requests
import time
import pandas as pd
import json
df = pd.DataFrame(columns=['id','content','is_good'])
count = 0
header = {
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36",
"Referer":"https://item.jd.com/100002980009.html",
"Cookie":"填自己的",
}
for i in range(0,500):
try:
url = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=100002980009&score=0&sortType=5&page=" + str(i) + "&pageSize=10&isShadowSku=0&fold=1"
r = requests.get(url,headers=header,timeout=10)
time.sleep(5)
d = r.text[20:-2]
d = json.loads(d)
print(i)
for j in range(10):
df.loc[count,'id'] = d['comments'][j]['id']
df.loc[count,'content'] = d['comments'][j]['content']
df.loc[count, 'is_good'] = d['comments'][j]['score']
count += 1
except:
print("出错了!")