python爬虫爬取哔哩哔哩动漫排行榜

python爬虫爬取哔哩哔哩动漫排行榜 爬取哔哩哔哩国产动漫排行榜的数据

一，要爬取的页面

二，代码

#coding=gbk
导入模块

```python
import io
import sys
import pandas as pd
import requests
from lxml import etree

url = "https://www.bilibili.com/v/popular/rank/guochan"

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
                  "Chrome/95.0.4638.69 Safari/537.36 Edg/95.0.1020.53 "
}
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='gb18030')
# 解决gbk问题

response = requests.get(url, headers=headers)
# print(response.text)

tree = etree.HTML(response.text)
divs = tree.xpath("/html/body/div[3]/div/div[2]/div[2]/ul")
# 确定位置
# print(divs)

for div in divs:
    div_name = div.xpath("./li/div[2]/div[2]/a/text()")
    # print(div_name)
    # 动漫名称
    div_number = div.xpath("./li/div[2]/div[2]/div[1]/text()")
    # print(div_number)
    # 更新到多少集

    div_amount = div.xpath("./li/div[2]/div[2]/div[2]/span[1]/text()")
    # print(div_amount)
    div_amount_01 = []
    for i in div_amount:
        div_amount_01.append(i.replace("n            ",""))
        #去除里面的换行和空格
    # print(div_amount_01)
    # 播放量
    div_comment = div.xpath("./li/div[2]/div[2]/div[2]/span[2]/text()")
    # print(div_comment)
    div_comment_01 = []
    for i in div_comment:
        div_comment_01.append(i.replace("n            ",""))
        # 
    # 评论
    div_give = div.xpath("./li/div[2]/div[2]/div[2]/span[3]/text()")
    # print(div_give)
    div_give_01 = []
    for i in div_give:
        div_give_01.append(i.replace("n            ",""))
    # 点赞
    div_heat = div.xpath("./li/div[2]/div[2]/div[3]/div/text()")
    # print(div_heat)
    # 综合评分
    title = {"动漫名称":div_name,"更新到多少集":div_number,"综合评分":div_heat,"播放量":div_amount_01,"评论":div_comment_01,"点赞":div_give_01}
    # 保存到字典里
    # print(title)
    df = pd.Dataframe(title)
    # 转换成Dataframe格式
    df.index = df.index+1
    # 索引从1开始
    df.to_excel("D:/安装包/哔哩哔哩动画.xlsx")
   	# 存放到excel中