【Python】爬取哔哩哔哩投稿信息

通过Python爬取哔哩哔哩稿件信息的脚本

import requests
from lxml import etree

L1 = []
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36'}


def getCode():
        url = ("http://www.bilibili.com/video/av" + avNo)
        code = requests.get(url, headers=headers)
        html = etree.HTML(code.text)

        # up主名字
        texts = html.xpath('//*[@id="v_upinfo"]/div[2]/div[1]/a[1]')

        if len(texts) < 1:
            up = "none"
        else:
            for index in range(len(texts)):
                if (index % 2) == 0:
                    up = texts[index].text

        # 投稿名字
        texts = html.xpath('//*[@id="viewbox_report"]/h1/span')
        if len(texts) < 1:
            name = "none"
        else:
            for index in range(len(texts)):
                if (index % 2) == 0:
                    name = texts[index].text

        # 投稿时间
        texts = html.xpath('//*[@id="v_upinfo"]/div[3]/div/span/span')
        if len(texts) < 1:
            playnum = "none"
        else:
            for index in range(len(texts)):
                if (index % 2) == 0:
                    playnum = texts[index].text
        print("av：", avNo, "up主:", up, "投稿名：", name,"粉丝数：",playnum)


if __name__ == '__main__':
    getCode()