def audio_crawler(path='songs'):
"""
音频爬取函数
:param path: 提供自定义下载路径修改
:return: None
"""
# 规定基础路径
base_dir = dirname(__file__) + "/" + path + "/"
# 如果路径不存在则创建路径
if not exists(base_dir):
mkdir(base_dir)
# 从12032-20000遍历sid，生成专辑url
for sid in range(12032, 20000):
# 拼接专辑url
url = "https://www.bilibili.com/audio/music-service-c/web/song/of-menu?sid={}&pn=1&ps=100".format(sid)
res = url_get(url=url, mode="json")
data = dict_get(res, "data")
# 如果data为空，则跳过
if data is None:
continue
items = dict_get(data, "data")
# 获取专辑信息请求
info_url = "https://www.bilibili.com/audio/music-service-c/web/menu/info?sid={}".format(sid)
info_get = url_get(url=info_url, mode="json")
album_title = dict_get(info_get, "title").replace("/", '').replace("<", '').replace(">", '').replace(
"|", '').replace(":", '').replace("*", '').replace("?", '').replace("\\", '')
# 如果路径不存在则创建路径
if not exists(base_dir + album_title):
mkdir(base_dir + album_title)
# 遍历专辑下所有音乐
for item in items:
author = dict_get(item, "author") # 歌手
title = dict_get(item, "title") # 音乐标题
sid = dict_get(item, "id") # 音乐id，用于拼接音乐下载url
songs_url = "https://www.bilibili.com/audio/music-service-c/web/url?sid={}".format(sid)
songs_get = url_get(url=songs_url, mode="json")
file_size = round(dict_get(songs_get, "size") / 1024 / 1024, 2) # 音频文件大小
# 分析json中cdns数据，判断音频文件真实地址
cdns = dict_get(songs_get, "cdns")
if cdns[0] > cdns[1]:
real_url = cdns[0]
else:
real_url = cdns[1]
print("Downloading Audio")
song_file_name = base_dir + album_title + "/" + title + " - " + author + '.m4a'
# 如果文件已存在，则跳过
if exists(song_file_name):
continue
# 下载音频文件
song_file_get = url_get(url=real_url, mode="content")
with open(song_file_name, "wb") as song:
song.write(song_file_get)
song.close()
# 显示进程信息
print("album_title: {}".format(album_title))
print("author: {}".format(author))
print("title: {}".format(title))
print("file_size: {} MB".format(file_size))
print("-" * 60)
def game_crawler():
database = Database("localhost", "root", "", "bilibili")
table_name = "game_list"
game_list_url = "https://game.bilibili.com/gamelist.json"
game_list_json = url_get(game_list_url, "json")
for game in game_list_json:
game_info = {}
game_info['name'] = dict_get(game, "title")
game_info['summary'] = dict_get(game, "summary")
game_info['website'] = dict_get(game, "website")
if database.execute_sql(table_name=table_name,
key="name",
value=game_info['name']) != 0:
print("{} 重复，跳过".format(game_info['name']))
print("-" * 60)
if database.execute_sql(table_name=table_name,
mode="insert",
keys=list(game_info.keys()),
values=list(game_info.values())):
print("游戏名: {}".format(game_info['name']))
print("游戏介绍: {}".format(game_info['summary']))
print("游戏官网: {}".format(game_info['website']))
print("-" * 60)
def crawler(av):
database = Database(host="localhost",
username="******",
password="",
db_name="bilibili")
for av_num in range(av, 48544470):
url = "https://api.bilibili.com/x/web-interface/view?aid={}".format(
av_num)
get_json = url_get(url=url, mode="json")
if dict_get(get_json, "code") != 0:
print('错误！没有此视频！av:{}'.format(av_num))
print('-' * 60)
continue
data = {}
data['video_av'] = str(av_num)
data['video_up'] = dict_get(get_json, "name")
data['video_title'] = dict_get(get_json, "title")
data['video_classification'] = dict_get(get_json, "tname")
data['video_view'] = dict_get(get_json, "view")
data['video_share'] = dict_get(get_json, "share")
data['video_like'] = dict_get(get_json, "like")
data['video_favorite'] = dict_get(get_json, "favorite")
data['video_coin'] = dict_get(get_json, "coin")
data['video_update'] = strftime("%Y-%m-%d %H:%M:%S",
gmtime(dict_get(get_json, "ctime")))
data['video_reply'] = dict_get(get_json, "reply")
data['video_danmaku'] = dict_get(get_json, "danmaku")
video_reprint = dict_get(get_json, "no_reprint")
if video_reprint == 0:
data['video_reprint'] = "转载"
else:
data['video_reprint'] = "原创"
db_select = database.execute_sql(table_name="video",
mode="search",
key="video_av",
value=data['video_av'])
if db_select != 0:
print('错误！此视频已存在！av:{}'.format(av_num))
print('-' * 60)
else:
if database.execute_sql(table_name="video",
mode="insert",
keys=list(data.keys()),
values=list(data.values())):
print("视频av号: {}".format(data['video_av']))
print("作者: {}".format(data['video_up']))
print("标题: {}".format(data['video_title']))
print("视频分类: {}".format(data['video_classification']))
print("观看数: {}".format(data['video_view']))
print("分享数: {}".format(data['video_share']))
print("点赞数: {}".format(data['video_like']))
print("收藏数: {}".format(data['video_favorite']))
print("投币数: {}".format(data['video_coin']))
print("上传时间: {}".format(data['video_update']))
print("评论数: {}".format(data['video_reply']))
print("弹幕数: {}".format(data['video_danmaku']))
print("性质: {}".format(data['video_reprint']))
print("-" * 60)
def crawler(type_, sort, path='save_picture', page_num=0):
"""
:param type_: 分类 --> cos or sifu
:param sort: 排序 --> hot or new
:param path: 路径（当前目录下）
:param page_num: 开始页，默认0页开始
"""
if path != '' and not exists(path):
mkdir(path)
base_dir = dirname(__file__) + "/" + path + "/"
url = "https://api.vc.bilibili.com/link_draw/v2/Photo/list?category={}&type={}&page_num={}&page_size=20".format(
type_, sort, page_num)
res = url_get(url=url, mode="json")
items = dict_get(res, "items")
if len(items) == 0:
print("Current page have no any picture, Exit mission!")
return
for i in items:
title = dict_get(i, "title") # 相簿标题
up = dict_get(i, "name") # up主
directory_name = title.replace("/", '').replace("<", '').replace(
">", '').replace("|", '').replace(":", '').replace(
"*", '').replace("?", '').replace("\\", '') + "-" + up
if not exists(path + "/" + directory_name):
mkdir(path + "/" + directory_name)
picture_list = [] # 存放图片地址
for picture in dict_get(i, "pictures"):
picture_list.append(picture['img_src'])
print("Downloading Pictures")
for pic in picture_list:
pic_name = pic.split("/")[-1]
full_pic_path = base_dir + directory_name + "/" + pic_name
if not exists(full_pic_path):
pic_get = url_get(url=pic, mode="content")
with open(full_pic_path, "wb") as pic_file:
pic_file.write(pic_get)
else:
continue
print("current page: {}".format(page_num + 1))
print("title: {}".format(title))
print("up: {}".format(up))
print("picture: {}".format(len(picture_list)))
print("-" * 60)
crawler(type_=type_, sort=sort, path=path, page_num=page_num + 1)
def column_crawler():
database = Database("localhost", "root", "", "bilibili")
table_name = "zhuanlan"
cid_dict = {
"动画": 2,
"游戏": 1,
"影视": 28,
"生活": 3,
"兴趣": 29,
"轻小说": 16,
"科技": 17,
}
for v in cid_dict.values():
pn = 1
while True:
column_url = "https://api.bilibili.com/x/article/recommends?cid={}&pn={}&ps=100&sort=0".format(
v, pn)
column_get = url_get(column_url, mode="json")
column_data = dict_get(column_get, "data")
if len(column_data) == 0:
print(pn)
break
for item in column_data:
data = {}
author_info = dict_get(item, "author") # 作者信息
data['author_mid'] = author_info['mid'] # 作者id
data['author_name'] = author_info['name'] # 作者用户名
data['category'] = dict_get(item, "category")['name'] # 所属分类
data['update_time'] = strftime(
"%Y-%m-%d %H:%M:%S",
localtime(dict_get(item, 'update_time'))) # 上传时间
data['art_id'] = dict_get(
item, "id"
) # 文章id，如果需要爬取文章内容可以拼接url: https://www.bilibili.com/read/cv[文章id]
data['art_title'] = dict_get(item, "title") # 文章标题
data['art_words'] = dict_get(item, "words") # 文章字数
data['art_like'] = dict_get(item, "like") # 文章点赞数
data['art_reply'] = dict_get(item, "reply") # 文章评论数
data['art_view'] = dict_get(item, "view") # 文章浏览数
data['art_favorite'] = dict_get(item, "favorite") # 文章收藏数
data['art_coin'] = dict_get(item, "coin") # 文章投币数
data['art_share'] = dict_get(item, "share") # 文章分享数
data['art_summary'] = dict_get(item, "summary") # 文章摘要
data['crawl_time'] = strftime("%Y-%m-%d %H:%M:%S",
localtime()) # 爬取时间
if database.execute_sql(table_name=table_name,
select="id",
key="art_id",
value=data['art_id']) != 0:
print("id:{} 重复，跳过".format(data['art_id']))
print("-" * 60)
# pn += 1
continue
if database.execute_sql(table_name=table_name,
mode="insert",
keys=list(data.keys()),
values=list(data.values())):
print("作者id: {}".format(data['author_mid']))
print("作者用户名: {}".format(data['author_name']))
print("所属分类: {}".format(data['category']))
print("上传时间: {}".format(data['update_time']))
print("文章id: {}".format(data['art_id']))
print("文章标题: {}".format(data['art_title']))
print("文章字数: {}".format(data['art_words']))
print("文章点赞数: {}".format(data['art_like']))
print("文章评论数: {}".format(data['art_reply']))
print("文章浏览数: {}".format(data['art_view']))
print("文章收藏数: {}".format(data['art_favorite']))
print("文章投币数: {}".format(data['art_coin']))
print("文章分享数: {}".format(data['art_share']))
print("文章摘要: {}".format(data['art_summary']))
print("爬取时间: {}".format(data['crawl_time']))
print("-" * 60)
else:
print("id:{} 异常，跳过".format(data['art_id']))
print("-" * 60)
# pn += 1
continue
pn += 1
def member_crawler(mid):
database = Database("localhost", "root", "", "bilibili")
while True:
follow_url = "https://api.bilibili.com/x/relation/stat?vmid={}".format(
mid)
view_url = "https://api.bilibili.com/x/space/upstat?mid={}".format(mid)
info_url = "https://api.bilibili.com/x/space/acc/info?mid={}".format(
mid)
tag_url = "https://space.bilibili.com/ajax/member/getTags?mids={}".format(
mid)
charging_url = "https://elec.bilibili.com/api/query.rank.do?mid={}".format(
mid)
upload_data_url = "https://api.bilibili.com/x/space/navnum?mid={}".format(
mid)
try:
member_info = url_get(info_url, mode='json')
username = dict_get(member_info, "name")
if username is None:
print("该会员不存在, 跳过 {}".format(mid))
print("-" * 60)
mid += 1
continue
level = dict_get(member_info, "level")
member_id = dict_get(member_info, "mid")
sex = dict_get(member_info, "sex")
coins = dict_get(member_info, "coins")
official_data = dict_get(member_info, "official")
follow_data = url_get(follow_url, mode="json")
following = dict_get(follow_data, 'following')
follower = dict_get(follow_data, 'follower')
view = dict_get(url_get(view_url, mode="json"), "view")
if official_data['role'] == 1:
official = official_data['title']
else:
official = "暂无认证"
birthday = dict_get(member_info, "birthday")
sign = dict_get(member_info, "sign")
vip = dict_get(member_info, "status")
if vip == 1:
vip_status = "是"
else:
vip_status = "否"
tag = ''
for x in dict_get(url_get(tag_url, mode="json"), "tags"):
tag += x + ' '
charging = dict_get(url_get(charging_url, mode="json"),
"total_count")
video_upload = dict_get(url_get(upload_data_url, mode="json"),
"video")
if database.execute_sql(table_name="member",
mode="search",
key="member_id",
value=member_id) != 0:
print("该会员已存在, 跳过 {}".format(member_id))
print("-" * 60)
mid += 1
continue
insert_data = {
"member_id": member_id,
"username": username,
"sex": sex,
"birthday": birthday,
"level": level,
"coins": coins,
"sign": sign,
"charging": charging,
"video_upload": video_upload,
"tag": tag,
"vip_status": vip_status,
"official": official,
"following": following,
"follower": follower,
"view": view,
}
if database.execute_sql(mode="insert",
table_name="member",
keys=list(insert_data.keys()),
values=list(insert_data.values())):
print("用户id: {}".format(member_id))
print("用户名: {}".format(username))
print("性别: {}".format(sex))
print("生日: {}".format(birthday))
print("等级: {}".format(level))
print("B币: {}".format(coins))
print("个人签名: {}".format(sign))
print("充电人数: {}".format(charging))
print("视频数量: {}".format(video_upload))
print("标签: {}".format(tag))
print("B站大会员: {}".format(vip_status))
print("Bilibili认证: {}".format(official))
print("关注数: {}".format(following))
print("粉丝数: {}".format(follower))
print("播放量: {}".format(view))
print("-" * 60)
mid += 1
except Exception as e:
print("错误, 跳过 mid={}".format(mid))
print(e)
print("-" * 60)
mid += 1
continue
def rank_crawler():
# 保存目录
save_path = "rank"
# 如果目录不存在则创建目录
if not exists(save_path):
mkdir(save_path)
# rid字典
rid_dict = {
"全站": 0,
"动画": 1,
"国创相关": 168,
"音乐": 3,
"舞蹈": 129,
"游戏": 4,
"科技": 36,
"数码": 188,
"生活": 160,
"鬼畜": 119,
"时尚": 155,
"娱乐": 5,
"影视": 181,
}
# 排行时间字典
day_dict = {
"日排行": 1,
"三日排行": 3,
"周排行": 7,
"月排行": 30,
}
# 遍历rid字典
for k, v in rid_dict.items():
rid = v
# 遍历排行时间字典
for k2, v2 in day_dict.items():
day = v2
# 拼接url
url = "https://api.bilibili.com/x/web-interface/ranking?rid={}&day={}".format(rid, day)
res = url_get(url=url, mode="json")
rank_list = dict_get(res, "list")
for i in range(len(rank_list)):
aid = dict_get(rank_list[i], "aid") # 视频id
author = dict_get(rank_list[i], "author") # up主
coins = dict_get(rank_list[i], "coins") # 投币数
play = dict_get(rank_list[i], "play") # 播放数
pts = dict_get(rank_list[i], "pts") # 综合得分
title = dict_get(rank_list[i], "title") # 视频标题
video_review = dict_get(rank_list[i], "video_review") # 视频弹幕数（？）
no_reprint = dict_get(rank_list[i], "no_reprint")
if no_reprint == 1: # 判断是否原创
reprint = "原创"
else:
reprint = "转载"
# 将数据保存到txt文件中，也可以导入functions.database包将数据保存到数据库中
with open("{}/Bilibili-{}-{}.txt".format(save_path, k, k2), "a+", encoding="utf-8") as data_file:
data_file.write("排名: {}\n".format(i + 1))
data_file.write("视频id: {}\n".format(aid))
data_file.write("up主: {}\n".format(author))
data_file.write("投币数: {}\n".format(coins))
data_file.write("播放数: {}\n".format(play))
data_file.write("综合得分: {}\n".format(pts))
data_file.write("视频标题: {}\n".format(title))
data_file.write("视频弹幕数: {}\n".format(video_review))
data_file.write("是否原创: {}\n".format(reprint))
data_file.write("-" * 60 + "\n")
data_file.close()
# 打印进程显示
print("排名: {}".format(i + 1))
print("视频id: {}".format(aid))
print("up主: {}".format(author))
print("投币数: {}".format(coins))
print("播放数: {}".format(play))
print("综合得分: {}".format(pts))
print("视频标题: {}".format(title))
print("视频弹幕数: {}".format(video_review))
print("是否原创: {}".format(reprint))
print("-" * 60)
def micro_video_crawler(order='', page_num=1):
"""
:param order: 排序方式，new为按照视频上传时间排序，默认为系统推荐
"""
database = Database("localhost", "root", "", "bilibili")
table_name = "micro_video"
classification = []
# 获取所有分类
classification_url = "https://api.vc.bilibili.com/clip/v1/video/zonelist?page=total"
classification_json = url_get(classification_url, "json")
classification_data = dict_get(classification_json, "data")
for i in classification_data:
if classification_data[i] == '':
continue
for j in classification_data[i]['tags']:
classification.append(j)
for tag in classification:
ps = 50 # page_size最大50
pn = page_num # 开始页，调用时可自定义
while True:
next_offset = (pn - 1) * ps
micro_video_url = "https://api.vc.bilibili.com/clip/v1/video/search?" \
"page_size={}&need_playurl=0&next_offset={}&order={}" \
"&tag={}".format(ps, next_offset, order, tag)
micro_video_json = url_get(micro_video_url, "json")
items = dict_get(micro_video_json, "items")
if len(items) == 0:
break
for item in items:
video_info = {"tag": tag}
video_info['title'] = dict_get(item, "description").replace("\n", "") # 视频标题
video_info['video_id'] = dict_get(item, "id") # 视频id
video_info['reply'] = dict_get(item, "reply") # 视频评论数
video_info['upload_time'] = dict_get(item, "upload_time") # 视频上传时间
video_info['video_size'] = round(float(dict_get(item, "video_size")) / 1024**2, 2) # 视频文件大小，单位mb（float）
video_info['video_time'] = dict_get(item, "video_time") # 视频时长，单位s
video_info['video_playurl'] = dict_get(item, "video_playurl") # 视频播放地址
video_info['watched_num'] = dict_get(item, "watched_num") # 视频播放数
video_info['name'] = dict_get(item, "name") # 上传者用户名
video_info['uid'] = dict_get(item, "uid") # 上传者uid
# 如果需要下载视频，请把下面注释去掉
# video_content = url_get(video_info['video_playurl'], "content") # 获取视频内容
# video_file_name = video_info['title'][:30].replace("/", '').replace("<", '').replace(">", '').replace(
# "|", '').replace(":", '').replace("*", '').replace("?", '').replace("\\", '') + ".mp4" # 拼接视频文件名
# # 保存视频
# with open(video_file_name, "wb") as video_file:
# video_file.write(video_content)
# video_file.close()
# 如果不需要插入数据库，请把下面部分注释掉
if database.execute_sql(table_name=table_name, key="video_id", value=video_info['video_id']) != 0:
print("视频id：{} 重复，跳过".format(video_info['video_id']))
print("-" * 60)
continue
if database.execute_sql(table_name=table_name, mode="insert",
keys=list(video_info.keys()), values=list(video_info.values())):
print("视频标题: {}".format(video_info['title']))
print("视频id: {}".format(video_info['video_id']))
print("视频评论数: {}".format(video_info['reply']))
print("视频上传时间: {}".format(video_info['upload_time']))
print("视频大小（mb）: {}".format(video_info['video_size']))
print("视频时长: {}".format(video_info['video_time']))
print("视频播放地址: {}".format(video_info['video_playurl']))
print("视频观看数: {}".format(video_info['watched_num']))
print("上传者用户名: {}".format(video_info['name']))
print("上传者id: {}".format(video_info['uid']))
print("-" * 60)
pn += 1
