python爬取b站三国演义弹幕

一、爬取三国弹幕

代码如下（示例）：

import requests
import re
from bs4 import BeautifulSoup as BS
import os
import csv
path = 'every_danmu'
if os.path.exists(path) == False:
    os.makedirs(path)
os.chdir(path)


def gethtml(url, header):
    r = requests.get(url, headers=header)
    r.encoding = 'utf-8'
    return r.text


def crawl_comments(r_text):
    txt1 = gethtml(url, header)
    pat = '"cid":(\d+)'
    chapter_total = re.findall(pat, txt1)[1:-2]
    count = 1
    for chapter in chapter_total:
        url_base = 'http://comment.bilibili.com/{}.xml'.format(chapter)
        txt2 = gethtml(url_base, header)
        soup = BS(txt2, 'lxml')
        all_d = soup.find_all('d')
        with open('{}.txt'.format(count), 'w', encoding='utf-8') as f:
            for d in all_d:
                f.write(d.get_text() + '\n')

        print('第{}话弹幕写入完毕'.format(count))
        count += 1


if __name__ == '__main__':
    url = 'https://www.bilibili.com/bangumi/play/ep327584?from=search&seid=7835316937688645380'
    header = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.102 Safari/537.36'}
    r_text = gethtml(url, header)
    crawl_comments(r_text)

2.最终结果

---