import requests  # 數(shù)據(jù)請(qǐng)求模塊 第三方模塊 pip install requests
import re  # 正則表達(dá)式模塊 內(nèi)置模塊 不需要安裝

# # 1. 發(fā)送請(qǐng)求
# url = '（評(píng)論看）'
# # headers 請(qǐng)求頭 作用把Python代碼進(jìn)行偽裝, 模擬成瀏覽器去發(fā)送請(qǐng)求
# # user-agent 瀏覽器基本身份標(biāo)識(shí)
# # headers 請(qǐng)求頭 字典數(shù)據(jù)類型
# headers = {
#     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.93 Safari/537.36'
# }
# # 通過(guò)requests模塊里面get請(qǐng)求方法, 對(duì)于url地址發(fā)送請(qǐng)求, 并且攜帶上headers請(qǐng)求頭, 最后用response變量去接收返回?cái)?shù)據(jù)
# response = requests.get(url=url, headers=headers)
# response.encoding = response.apparent_encoding
# # <Response [200]> response對(duì)象 200狀態(tài)碼 表示請(qǐng)求成功
# # 如果你想要獲取 網(wǎng)頁(yè)源代碼一樣的數(shù)據(jù)內(nèi)容的話, 是獲取響應(yīng)體的文本數(shù)據(jù)
# # 如果服務(wù)器返回的數(shù)據(jù), 不是完整json數(shù)據(jù) 字典數(shù)據(jù) 直接獲取response.json()就會(huì)報(bào)錯(cuò)
# # 2. 獲取數(shù)據(jù) response.text 返回?cái)?shù)據(jù) html字符串?dāng)?shù)據(jù)
# # print(response.text)
# # 3. 解析數(shù)據(jù), 解析方式  re[可以直接對(duì)于字符串?dāng)?shù)據(jù)進(jìn)行提取] css xpath [主要根據(jù)標(biāo)簽屬性/節(jié)點(diǎn)提取數(shù)據(jù)]
# # () 精確匹配 表示想要的數(shù)據(jù) 泛匹配 .*? 正則表達(dá)式元字符 可以匹配任意字符(除了換行符\n以外)
# data_list = re.findall('<d p=".*?">(.*?)</d>', response.text)
# for index in data_list:
#     # mode 保存方式 encoding 編碼
#     # pprint.pprint() 格式化輸入 json字典數(shù)據(jù)
#     with open('彈幕.txt', mode='a', encoding='utf-8') as f:
#         f.write(index)
#         f.write('\n')
#         print(index)

url = 'https://mapi.vip.com/vips-mobile/rest/shopping/pc/search/product/rank?callback=getMerchandiseIds&app_name=shop_pc&app_version=4.0&warehouse=VIP_NH&fdc_area_id=104104101&client=pc&mobile_platform=1&province_id=104104&api_key=70f71280d5d547b2a7bb370a529aeea1&user_id=&mars_cid=1634797375792_17a23bdc351b36f2915c2f7ec16dc88e&wap_consumer=a&standby_id=nature&keyword=%E5%8F%A3%E7%BA%A2&lv3CatIds=&lv2CatIds=&lv1CatIds=&brandStoreSns=&props=&priceMin=&priceMax=&vipService=&sort=0&pageOffset=0&channelId=1&gPlatform=PC&batchSize=120&_=1639640088314'

headers = {
    'referer': 'https://category.vip.com/',
    'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.93 Safari/537.36'
}
response = requests.get(url=url, headers=headers)
print(response.text)

import jieba  # 結(jié)巴分詞 pip install jieba
import wordcloud  # 詞云圖 pip install wordcloud
import imageio  # 讀取本地圖片 修改詞云圖形
img = imageio.imread('蘋果.png')

f = open('彈幕.txt', encoding='utf-8')
text = f.read()
# print(text)

text_list = jieba.lcut(text)
print(text_list)
# 列表轉(zhuǎn)成字符串
text_str = ' '.join(text_list)
print(text_str)

wc = wordcloud.WordCloud(
    width=500,  # 寬度
    height=500,  # 高度
    background_color='white', # 背景顏色
    mask=img,
    stopwords={'每', '一個(gè)', '了', '的', '夢(mèng)想', '助力'},
    font_path='msyh.ttc'  # 字體文件
)

wc.generate(text_str)
wc.to_file('詞云1.png')