【Python实战】爬b站edg夺guand幕

【Python实战】爬b站edg夺guand幕

把headers里面的headers和cookie改成自己的就好了

有不懂的地方可以在下面评论留言

import requests
import re
import jieba
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import time
# BV1EP4y1j7kV


def get_cid(bv):
    headers = {
        "user-agent": ""
    }
    resp = requests.get("https://api.bilibili.com/x/player/pagelist?bvid={}&jsonp=jsonp".format(bv), headers=headers)
    resp = resp.json()
    cids = []
    for i in range(len(resp['data'])):
        cid = resp['data'][i]['cid']
        cids.append(cid)
    return cids


def get_days(bv, cid):
    headers = {
        "user-agent": "",
        "referer": "https://www.bilibili.com/video/{}".format(bv),
        "cookie": "",
        "origin": "https://www.bilibili.com"
    }
    # https://api.bilibili.com/x/v1/dm/list.so?oid=438198616
    # oid和cid是一个东西
    response = requests.get(url="https://api.bilibili.com/x/v2/dm/history/index?type=1&oid={}&month=2021-11".format(cid), headers=headers)
    json_data = response.json()
    days = json_data["data"]
    return days


def get_data(bv, days, cids):
    headers = {
        'user-agent': '',
        "referer": "https://www.bilibili.com/video/{}".format(bv),
        "cookie": "",
        "origin": "https://www.bilibili.com"
    }
    for cid in cids:
        for day in days:
            html = requests.get(url="https://api.bilibili.com/x/v2/dm/web/history/seg.so?type=1&oid={}&date={}".format(cid, day), headers=headers).text
            result = re.findall(".*?([u4E00-u9FA5]+).*?", html)
            time.sleep(1)
            print('{}完成{}的爬取'.format(cid, day))
            save_data(result, bv)


def save_data(result, bv):
    for i in result:
        with open('{}&B站d幕.txt'.format(bv), 'a', encoding='utf-8') as f:
            f.write(i)
            f.write('n')


def fenci(bv):
    with open('{}&B站d幕.txt'.format(bv), 'r', encoding='utf-8') as file:
        word = file.read()
    # jieba.add_word 添加特定的词进去
    with open('meaningless.txt', 'r', encoding='UTF-8') as meaningless_file:
        meaningless_set = set(meaningless_file.read().split('n'))
    meaningless_set.add(' ')
    word_list = list(jieba.lcut(word))
    word_set = set(word_list) - meaningless_set
    # 统计词频，存在字典中
    word_dict = {}
    for k in word_set:
        word_dict[k] = word_list.count(k)
    # 对词频进行排序
    word_list_sorted = list(word_dict.items())
    word_list_sorted.sort(key=lambda i: i[1], reverse=True)
    print(word_list_sorted)
    with open('{}-list_sorted.txt'.format(bv), 'a', encoding='utf-8') as f:
        for i in word_list_sorted[1:]:
            f.write(str(i))
            f.write('n')
    return word_list_sorted



if __name__ == '__main__':
    bv = ‘BV1EP4y1j7kV’
    cids = get_cid(bv)
    print(cids)
    days = get_days(bv, cids[0])
    print(days)
    get_data(bv, days, cids)
    fenci(bv)