百度飛槳小白逆襲大神之鯉魚躍龍門

這裏是三歲，轉眼間已經到了大作業了，成功與否最後一搏，最後給小白一點建議吧！加油！等到全部結束後回過頭再看一遍效果特別好，會發現忽然間恍然大悟！

綜合大作業

一：先爬取評論
二：數據處理，分詞，清洗
三：詞頻統計
四：詞雲生成

其他具體的在文章裏面已經很齊全了
不需要多說什麼了

小白專屬嘛，怕大家沒有爬取過評論，沒有做過詞雲，在這裏把前段時間做的B站up主評論爬取和中文詞雲製作模板給大家做以參考

'''
B站爬取
https://api.bilibili.com/x/v1/dm/list.so?oid=837806779 彈幕api
https://api.bilibili.com/x/v2/reply?type=1&oid=837806779&&pn=1 評論api
彈幕只能夠用oid，目前抓包未在到oid集中出現地址
bug:部分網站沒有那麼嚴格按照['data']['replies']['content']['message']的順序來
'''
#導入庫
import requests
from bs4 import BeautifulSoup
import re
import json


def Gethtml(url): #獲取網頁
    kv = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.113 Safari/537.36"}
    r = requests.get(url, headers = kv)
    # print(r.text)
    r.encoding = r.apparent_encoding
    # print(r.text)
    return r.text


#獲取up的uid
def u_id(uid_html):
    # url = f"https://search.bilibili.com/all?keyword={name}"
    # r = Gethtml(url)
    # print(r)
    # r = requests.get(url, headers=kv)
    html = BeautifulSoup(uid_html,'lxml')
    # print(html)
    uid = html.find(name = 'a',attrs = {"class":"title"})
    # print(uid)
    #uid = '<a class="title" href="//space.bilibili.com/390461123?from=search" target="_blank" title="徐大sao">徐大sao</a>'
    uid = re.findall(r'<a.*?href="//space.bilibili.com/(.+)f.*',str(uid))
    uid = uid[0][:-1]
    print('以獲取up主的id爲',uid)
    return uid


def a_id(aid_html):#文章的aid
        videos = json.loads(aid_html)
        # print(videos)
        videos_lists = videos['data']['list']['vlist']
        aid_list = []
        for videos_list in videos_lists:
            aid = videos_list['aid']
            aid_list.append(aid)
        print('已獲得視頻id長度爲：',len(aid_list))
        return aid_list
 
def comment_save(name, comment_html):  #爬取每個視頻下的評論
        videos = json.loads(comment_html.text)
        videos_lists = videos['data']['replies']#['replies']['content']
        # print(videos_lists)
        bvid_list = []
        if videos_lists :
            for videos_list in videos_lists:
                bvid = videos_list['content']['message']
                bvid_list.append(bvid)
                print(bvid_list)
                with open(f'{name}.txt','a+',encoding ='utf-8') as f:
                    f.write(bvid)

        print('提取完畢！')


def main(name): #主函數
    #獲得阿婆主的id
    url_uid = f"https://search.bilibili.com/all?keyword={name}"
    uid_html = Gethtml(url_uid)
    uid = u_id(uid_html)
    # print(uid)

    # 循環獲取至少9頁的視頻（不一定有那麼多）
    for i in range(1,10):
        aid_url = f"https://api.bilibili.com/x/space/arc/search?mid={uid}&ps=30&tid=0&pn={i}&keyword=&order=pubdate&jsonp=jsonp"
        aid_html = Gethtml(aid_url)
        aid_list = a_id(aid_html)
    # print(aid_list)

    #獲取保存評論
        for j in range(len(aid_list)):
            for i in range(1,15):
                comment_uil = f"https://api.bilibili.com/x/v2/reply?type=1&oid={aid_list[j]}&&pn={i}"
                comment_html = requests.get(comment_uil)
                comment_save(name, comment_html)

            # print(comment_html)


main('敬漢卿')#調用主函數
#賢寶寶baby
#老師好我叫何同學
#大祥哥來了
#女胖胖
#記錄生活的蛋黃派

詞雲生成器（自己修改）

from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import jieba
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator

d = path.dirname(__file__)

# Read the whole text. encoding = ' gbk'或'utf-8'
#文檔地址
f = open("D:\python3.7.4\爬蟲\女胖胖.txt", 'r' , encoding = ' utf-8')
t = f.read()
ls = jieba.lcut(t)
text = ' '.join(ls)
#線下詞雲圖必須是png格式白底的不然不好看！
alice_coloring = np.array(Image.open(path.join(d, "手繪美女.png")))

# 設置停用詞這裏面原來是英文的需要自己添加，中文的停用詞太多自己網上找
stopwords = set(STOPWORDS)
stopwords.add(" ")
# print(stopwords)
# 你可以通過 mask 參數 來設置詞雲形狀
wc = WordCloud(background_color="white",font_path = "msyh.ttc" , max_words=2000, mask=alice_coloring,
               stopwords=stopwords, max_font_size=40, random_state=42)
# generate word cloud
wc.generate(text)

# create coloring from image
image_colors = ImageColorGenerator(alice_coloring)

# show
# 在只設置mask的情況下,你將會得到一個擁有圖片形狀的詞雲
plt.imshow(wc, interpolation="bilinear")
plt.axis("off")
plt.figure()
# recolor wordcloud and show
# we could also give color_func=image_colors directly in the constructor
# 我們還可以直接在構造函數中直接給顏色
# 通過這種方式詞雲將會按照給定的圖片顏色佈局生成字體顏色策略
plt.imshow(wc.recolor(color_func=image_colors), interpolation="bilinear")
plt.axis("off")
plt.figure()
plt.imshow(alice_coloring, cmap=plt.cm.gray, interpolation="bilinear")
plt.axis("off")
plt.show()

李子柒最後的詞雲圖，因爲數據處理太麻煩，沒有好好處理，大家多多包涵！！！

大家加油！時間不多，還得多多努力！！！奧利給！