基于Python的淘宝评论爬虫

基于 Python 实现的淘宝商品评论爬虫，核心目标是爬取指定淘宝商品的评论数据（评论内容、评分、买家昵称、评论时间等），并保证代码可运行、易理解，同时适配淘宝的反爬机制。

实现思路

前置准备

pip install requests json5 pandas

完整代码

import requests
import json5
import csv
import time
import random
from urllib.parse import urlencode

# ————————– 配置项 ————————–
ITEM_ID = "690907351225" # 淘宝商品ID（从商品链接中提取）
PAGE_NUM = 5 # 要爬取的评论页数（淘宝单页20条评论）
CSV_FILE = "taobao_comments.csv" # 保存评论的CSV文件名
# 替换为你自己的淘宝Cookie（必须！否则请求会被拦截）
COOKIE = "你的淘宝Cookie，完整复制"

# ————————– 请求头配置 ————————–
HEADERS = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
"Cookie": COOKIE,
"Referer": f"https://item.taobao.com/item.htm?id={ITEM_ID}",
"Accept": "application/json, text/javascript, */*; q=0.01",
"Accept-Language": "zh-CN,zh;q=0.9",
"X-Requested-With": "XMLHttpRequest",
"Connection": "keep-alive"
}

def get_taobao_comments(item_id, page):
"""
获取单页淘宝评论数据
:param item_id: 商品ID
:param page: 页码
:return: 评论列表（字典格式）
"""
# 构造动态参数（_ksTS 是时间戳+随机数，callback 是固定格式）
timestamp = str(int(time.time() * 1000))
random_str = str(random.randint(100, 999))
_ksTS = f"{timestamp}_{random_str}"
callback = f"jsonp{random.randint(100000, 999999)}"

# 淘宝评论接口参数
params = {
"callback": callback,
"ajax": "true",
"m": "customized",
"platelet": "true",
"productId": item_id,
"page": page,
"pageSize": 20,
"rateType": "", # 空=全部评论，1=好评，2=中评，3=差评
"orderType": "sort_weight", # sort_weight=综合排序，create=最新排序
"showContent": "true",
"_ksTS": _ksTS,
"defaultSearch": "ppctag",
"isInner": "false"
}

# 评论接口URL
url = f"https://rate.taobao.com/feedRateList.htm?{urlencode(params)}"

try:
# 发送请求（添加超时控制）
response = requests.get(url, headers=HEADERS, timeout=15)
response.raise_for_status() # 抛出HTTP错误（如403/500）

# 处理JSONP数据：去掉回调函数包裹，提取核心JSON
json_data_str = response.text.lstrip(f"{callback}(").rstrip(");")
# 使用json5解析（兼容淘宝返回的非标准JSON）
data = json5.loads(json_data_str)

# 提取评论数据
comments = []
if "comments" in data and data["comments"]:
for comment in data["comments"]:
comment_info = {
"买家昵称": comment.get("nick", ""),
"评论内容": comment.get("content", "").replace("\\n", "").strip(),
"评分": comment.get("rate", 0),
"评论时间": comment.get("date", ""),
"点赞数": comment.get("useful", 0),
"追评内容": comment.get("appendComment", {}).get("content", "").replace("\\n", "").strip(),
"追评时间": comment.get("appendComment", {}).get("date", "")
}
comments.append(comment_info)

return comments

except requests.exceptions.RequestException as e:
print(f"第{page}页请求失败：{e}")
return []
except json5.JSON5DecodeError as e:
print(f"第{page}页数据解析失败（可能Cookie过期）：{e}")
return []
except Exception as e:
print(f"第{page}页未知错误：{e}")
return []

def save_to_csv(comments, file_path):
"""
将评论数据保存为CSV文件（UTF-8编码，避免中文乱码）
"""
if not comments:
return

# 表头（与评论字典的key对应）
headers = ["买家昵称", "评论内容", "评分", "评论时间", "点赞数", "追评内容", "追评时间"]

# 追加模式写入，避免覆盖
with open(file_path, "a", encoding="utf-8-sig", newline="") as f:
writer = csv.DictWriter(f, fieldnames=headers)
# 若文件为空，先写表头
if f.tell() == 0:
writer.writeheader()
writer.writerows(comments)

if __name__ == "__main__":
print(f"开始爬取淘宝商品{ITEM_ID}的评论，共{PAGE_NUM}页…")

# 清空原有CSV文件（可选）
with open(CSV_FILE, "w", encoding="utf-8-sig", newline="") as f:
pass

total = 0
for page in range(1, PAGE_NUM + 1):
print(f"正在爬取第{page}页…")
comments = get_taobao_comments(ITEM_ID, page)

if comments:
save_to_csv(comments, CSV_FILE)
total += len(comments)
print(f"第{page}页爬取成功，共{len(comments)}条评论")
else:
print(f"第{page}页无有效评论（可能Cookie过期/页数超限）")

# 随机延时2-5秒，避免请求过快被封
time.sleep(random.uniform(2, 5))

print(f"\\n爬取完成！共获取{total}条评论，已保存至 {CSV_FILE}")

代码关键说明

常见问题解决

总结