Python练习：爬取B站排行榜数据

获取B站视频排行榜的一些数据，例如标题、UP主、分区、BV号、播放量、弹幕量、评论量、综合得分等

同时将视频封面保存到本地

import re
import requests
import os
from requests.packages.urllib3.exceptions import InsecureRequestWarning
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)

url="https://www.bilibili.com/v/popular/rank/all"
img_list=[] # 图片链接
name_list=[] # 标题
tname_list=[] # 分区
view_list=[] # 播放量
up_list=[] # UP名
pinglun_list=[] # 评论量
socre_list=[] # 综合得分
bv_list=[] # bv号


def get_URL():
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36'}
    response = requests.get(url=url, headers=headers, verify=False)
    content = response.content.decode('utf-8')
    return content

def get_IMG():
    content=get_URL()
    pattern = re.compile(r'"pic":"(.*?)","title"')
    imgdata_list = pattern.findall(content)
    for img in imgdata_list:
        img = img.encode('utf-8').decode('unicode_escape')
        img_list.append(img)
    print("封面链接: ")
    print(img_list)

def get_otherinfo():
    content = get_URL()
    # 视频标题
    pattern_name = re.compile(r'class="title">(.*?)</a>')
    name_list = pattern_name.findall(content)
    print("视频标题: ")
    print(name_list)
    # UP主名称
    pattern_upname = re.compile(r'"name":"(.*?)"')
    up_list = pattern_upname.findall(content)
    print("UP主名称: ")
    print(up_list)
    # 视频类型/分区
    pattern_tname = re.compile(r'"tname":"(.*?)"')
    tname_list = pattern_tname.findall(content)
    print("视频分区:")
    print(tname_list)
    # 播放量
    pattern_view = re.compile(r'"view":(.*?)"')
    view_list = pattern_view.findall(content)
    print("播放量:")
    print(view_list)
    # 弹幕量
    pattern_danmu = re.compile(r'"danmaku":(.*?)"')
    danmu_list = pattern_danmu.findall(content)
    print("弹幕量:")
    print(danmu_list)
    # BV号
    pattern_bv = re.compile(r'com/video/(.*?)" target="')
    bv_list = pattern_bv.findall(content)
    print("BV号:")
    print(bv_list)
    # 综合得分
    pattern_bv = re.compile(r'<div>(.*?)</div>综合得分')
    bv_list = pattern_bv.findall(content)
    print("综合得分:")
    print(bv_list)
    # "reply":114550,"favorite":76574,"coin":320357,"share":64088,""like":362596,"dislike":0}
    # 回复，收藏，硬币，分享，点赞，踩
def download():
    root = "pic/"
    for i in range(len(img_list)):
        path = root+str(i)+"."+'png'
        # 判断文件夹是否存在
        if not os.path.exists(root):
            os.mkdir(root)
        if not os.path.exists(path):
            # 发送请求
            r = requests.get(img_list[i])
            with open(path, 'wb') as f:
                f.write(r.content)
                f.close()

if __name__ == '__main__':
    get_IMG()
    download()
    get_otherinfo()