Python采集貓眼兩萬(wàn)條數(shù)據(jù) 對(duì)《無(wú)名之輩》影評(píng)進(jìn)行分析

def download(self, url):
 """下載html內(nèi)容"""

 print("正在下載URL: "+url)
 # 下載html內(nèi)容
 response = requests.get(url, headers=self.headers)

 # 轉(zhuǎn)成json格式數(shù)據(jù)
 if response.status_code == 200:
  return response.json()
 else:
  # print(html.status_code)
  print('下載數(shù)據(jù)為空！')
  return ""

def parse(self, content):
 """分析數(shù)據(jù)"""

 comments = []
 try:
  for item in content['cmts']:
  comment = {
   'nickName': item['nickName'], # 昵稱
   'cityName': item['cityName'], # 城市
   'content': item['content'],  # 評(píng)論內(nèi)容
   'score': item['score'],  # 評(píng)分
   'startTime': item['startTime'], # 時(shí)間
  }
  comments.append(comment)

 except Exception as e:
  print(e)

 finally:
  return comments

 def save(self, data):
  """寫(xiě)入文件"""
 
  print("保存數(shù)據(jù)，寫(xiě)入文件中...")
  self.save_file.write(data)

def start(self):
 """啟動(dòng)控制方法"""

 print("爬蟲(chóng)開(kāi)始...\r\n")

 start_time = self.start_time
 end_time = self.end_time

 num = 1
 while start_time > end_time:
  print("執(zhí)行次數(shù):", num)
  # 1、下載html
  content = self.download(self.target_url + str(start_time))

  # 2、分析獲取關(guān)鍵數(shù)據(jù)
  comments = ''
  if content != "":
  comments = self.parse(content)

  if len(comments) <= 0:
  print("本次數(shù)據(jù)量為：0，退出爬取！\r\n")
  break

  # 3、寫(xiě)入文件
  res = ''
  for cmt in comments:
  res += "%s###%s###%s###%s###%s\n" % (cmt['nickName'], cmt['cityName'], cmt['content'], cmt['score'], cmt['startTime'])
  self.save(res)

  print("本次數(shù)據(jù)量：%s\r\n" % len(comments))

  # 獲取最后一條數(shù)據(jù)的時(shí)間 ，然后減去一秒
  start_time = datetime.strptime(comments[len(comments) - 1]['startTime'], "%Y-%m-%d %H:%M:%S") + timedelta(seconds=-1)
  # start_time = datetime.strptime(start_time, "%Y-%m-%d %H:%M:%S")

  # 休眠3s
  num += 1
  time.sleep(3)

 self.save_file.close()
 print("爬蟲(chóng)結(jié)束...")

def createCharts(self):
 """生成圖表"""

 # 讀取數(shù)據(jù),格式：[{"北京", 10}, {"上海",10}]
 data = self.readCityNum()

 # 1 熱點(diǎn)圖
 geo1 = Geo("《無(wú)名之輩》觀眾位置分布熱點(diǎn)圖", "數(shù)據(jù)來(lái)源：貓眼，F(xiàn)ly采集", title_color="#FFF", title_pos="center", width="100%", height=600, background_color="#404A59")

 attr1, value1 = geo1.cast(data)

 geo1.add("", attr1, value1, type="heatmap", visual_range=[0, 1000], visual_text_color="#FFF", symbol_size=15, is_visualmap=True, is_piecewise=False, visual_split_number=10)
 geo1.render("files/無(wú)名之輩-觀眾位置熱點(diǎn)圖.html")

 # 2 位置圖
 geo2 = Geo("《無(wú)名之輩》觀眾位置分布", "數(shù)據(jù)來(lái)源：貓眼，F(xiàn)ly采集", title_color="#FFF", title_pos="center", width="100%", height=600,
   background_color="#404A59")

 attr2, value2 = geo1.cast(data)
 geo2.add("", attr2, value2, visual_range=[0, 1000], visual_text_color="#FFF", symbol_size=15,
  is_visualmap=True, is_piecewise=False, visual_split_number=10)
 geo2.render("files/無(wú)名之輩-觀眾位置圖.html")

 # 3、top20 柱狀圖
 data_top20 = data[:20]
 bar = Bar("《無(wú)名之輩》觀眾來(lái)源排行 TOP20", "數(shù)據(jù)來(lái)源：貓眼，F(xiàn)ly采集", title_pos="center", width="100%", height=600)
 attr, value = bar.cast(data_top20)
 bar.add('', attr, value, is_visualmap=True, visual_range=[0, 3500], visual_text_color="#FFF", is_more_utils=True, is_label_show=True)
 bar.render("files/無(wú)名之輩-觀眾來(lái)源top20.html")

 print("圖表生成完成")

def createWordCloud(self):
 """生成評(píng)論詞云"""
 comments = self.readAllComments() # 19185

 # 使用 jieba 分詞
 commens_split = jieba.cut(str(comments), cut_all=False)
 words = ''.join(commens_split)

 # 給詞庫(kù)添加停止詞
 stopwords = STOPWORDS.copy()
 stopwords.add("電影")
 stopwords.add("一部")
 stopwords.add("無(wú)名之輩")
 stopwords.add("一部")
 stopwords.add("一個(gè)")
 stopwords.add("有點(diǎn)")
 stopwords.add("覺(jué)得")

 # 加載背景圖片
 bg_image = plt.imread("files/2048_bg.png")

 # 初始化 WordCloud
 wc = WordCloud(width=1200, height=600, background_color='#FFF', mask=bg_image, font_path='C:/Windows/Fonts/STFANGSO.ttf', stopwords=stopwords, max_font_size=400, random_state=50)

 # 生成，顯示圖片
 wc.generate_from_text(words)
 plt.imshow(wc)
 plt.axis('off')
 plt.show()

def get_coordinate(self, name, region="中國(guó)", raise_exception=False):
 """
 Return coordinate for the city name.

 :param name: City name or any custom name string.
 :param raise_exception: Whether to raise exception if not exist.
 :return: A list like [longitude, latitude] or None
 """
 if name in self._coordinates:
  return self._coordinates[name]


 coordinate = get_coordinate(name, region=region)

 # [ 20181204 添加
 # print(name, coordinate)
 if coordinate is None:
  # 如果字典key匹配不上，嘗試進(jìn)行模糊查詢
  search_res = search_coordinates_by_region_and_keyword(region, name)
  # print("###",search_res)
  if search_res:
  coordinate = sorted(search_res.values())[0]
 # 20181204 添加 ]

 if coordinate is None and raise_exception:
  raise ValueError("No coordinate is specified for {}".format(name))

 return coordinate

# -*- coding:utf-8 -*-

import requests
from datetime import datetime, timedelta
import os
import time
import sys


class MaoyanFilmReviewSpider:
 """貓眼影評(píng)爬蟲(chóng)"""

 def __init__(self, url, end_time, filename):
  # 頭部
  self.headers = {
   'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A372 Safari/604.1'
  }

  # 目標(biāo)URL
  self.target_url = url

  # 數(shù)據(jù)獲取時(shí)間段，start_time:截止日期，end_time:上映時(shí)間
  now = datetime.now()

  # 獲取當(dāng)天的 零點(diǎn)
  self.start_time = now + timedelta(hours=-now.hour, minutes=-now.minute, seconds=-now.second)
  self.start_time = self.start_time.replace(microsecond=0)
  self.end_time = datetime.strptime(end_time, "%Y-%m-%d %H:%M:%S")

  # 打開(kāi)寫(xiě)入文件, 創(chuàng)建目錄
  self.save_path = "files/"
  if not os.path.exists(self.save_path):
   os.makedirs(self.save_path)
  self.save_file = open(self.save_path + filename, "a", encoding="utf-8")

 def download(self, url):
  """下載html內(nèi)容"""

  print("正在下載URL: "+url)
  # 下載html內(nèi)容
  response = requests.get(url, headers=self.headers)

  # 轉(zhuǎn)成json格式數(shù)據(jù)
  if response.status_code == 200:
   return response.json()
  else:
   # print(html.status_code)
   print('下載數(shù)據(jù)為空！')
   return ""

 def parse(self, content):
  """分析數(shù)據(jù)"""

  comments = []
  try:
   for item in content['cmts']:
    comment = {
     'nickName': item['nickName'],  # 昵稱
     'cityName': item['cityName'],  # 城市
     'content': item['content'],   # 評(píng)論內(nèi)容
     'score': item['score'],    # 評(píng)分
     'startTime': item['startTime'], # 時(shí)間
    }
    comments.append(comment)

  except Exception as e:
   print(e)

  finally:
   return comments

 def save(self, data):
  """寫(xiě)入文件"""

  print("保存數(shù)據(jù)，寫(xiě)入文件中...")
  self.save_file.write(data)

 def start(self):
  """啟動(dòng)控制方法"""

  print("爬蟲(chóng)開(kāi)始...\r\n")

  start_time = self.start_time
  end_time = self.end_time

  num = 1
  while start_time > end_time:
   print("執(zhí)行次數(shù):", num)
   # 1、下載html
   content = self.download(self.target_url + str(start_time))

   # 2、分析獲取關(guān)鍵數(shù)據(jù)
   comments = ''
   if content != "":
    comments = self.parse(content)

   if len(comments) <= 0:
    print("本次數(shù)據(jù)量為：0，退出爬取！\r\n")
    break

   # 3、寫(xiě)入文件
   res = ''
   for cmt in comments:
    res += "%s###%s###%s###%s###%s\n" % (cmt['nickName'], cmt['cityName'], cmt['content'], cmt['score'], cmt['startTime'])
   self.save(res)

   print("本次數(shù)據(jù)量：%s\r\n" % len(comments))

   # 獲取最后一條數(shù)據(jù)的時(shí)間 ，然后減去一秒
   start_time = datetime.strptime(comments[len(comments) - 1]['startTime'], "%Y-%m-%d %H:%M:%S") + timedelta(seconds=-1)
   # start_time = datetime.strptime(start_time, "%Y-%m-%d %H:%M:%S")

   # 休眠3s
   num += 1
   time.sleep(3)

  self.save_file.close()
  print("爬蟲(chóng)結(jié)束...")


if __name__ == "__main__":
 # 確保輸入?yún)?shù)
 if len(sys.argv) != 4:
  print("請(qǐng)輸入相關(guān)參數(shù)：[moveid]、[上映日期]和[保存文件名]，如：xxx.py 42962 2018-11-09 text.txt")
  exit()

 # 貓眼電影ID
 mid = sys.argv[1] # "1208282" # "42964"
 # 電影上映日期
 end_time = sys.argv[2] # "2018-11-16" # "2018-11-09"
 # 每次爬取條數(shù)
 offset = 15
 # 保存文件名
 filename = sys.argv[3]

 spider = MaoyanFilmReviewSpider(url="http://m.maoyan.com/mmdb/comments/movie/%s.json?v=yes&offset=%d&startTime=" % (mid, offset), end_time="%s 00:00:00" % end_time, filename=filename)
 # spider.start()

 spider.start()
 # t1 = "2018-11-09 23:56:23"
 # t2 = "2018-11-25"
 #
 # res = datetime.strptime(t1, "%Y-%m-%d %H:%M:%S") + timedelta(days=-1)
 # print(type(res))

MaoyanFilmReviewSpider.py

# -*- coding:utf-8 -*-
from pyecharts import Geo, Bar, Bar3D
import jieba
from wordcloud import STOPWORDS, WordCloud
import matplotlib.pyplot as plt


class ACoolFishAnalysis:
 """無(wú)名之輩 --- 數(shù)據(jù)分析"""
 def __init__(self):
  pass

 def readCityNum(self):
  """讀取觀眾城市分布數(shù)量"""
  d = {}

  with open("files/myCmts2.txt", "r", encoding="utf-8") as f:
   row = f.readline()

   while row != "":
    arr = row.split('###')

    # 確保每條記錄長(zhǎng)度為 5
    while len(arr) < 5:
     row += f.readline()
     arr = row.split('###')

    # 記錄每個(gè)城市的人數(shù)
    if arr[1] in d:
     d[arr[1]] += 1
    else:
     d[arr[1]] = 1 # 首次加入字典，為 1

    row = f.readline()


   # print(len(comments))
   # print(d)

  # 字典 轉(zhuǎn) 元組數(shù)組
  res = []
  for ks in d.keys():
   if ks == "":
    continue
   tmp = (ks, d[ks])
   res.append(tmp)

  # 按地點(diǎn)人數(shù)降序
  res = sorted(res, key=lambda x: (x[1]),reverse=True)
  return res

 def readAllComments(self):
  """讀取所有評(píng)論"""
  comments = []

  # 打開(kāi)文件讀取數(shù)據(jù)
  with open("files/myCmts2.txt", "r", encoding="utf-8") as f:
   row = f.readline()

   while row != "":
    arr = row.split('###')

    # 每天記錄長(zhǎng)度為 5
    while len(arr) < 5:
     row += f.readline()
     arr = row.split('###')

    if len(arr) == 5:
     comments.append(arr[2])

    # if len(comments) > 20:
    #  break
    row = f.readline()

  return comments

 def createCharts(self):
  """生成圖表"""

  # 讀取數(shù)據(jù),格式：[{"北京", 10}, {"上海",10}]
  data = self.readCityNum()

  # 1 熱點(diǎn)圖
  geo1 = Geo("《無(wú)名之輩》觀眾位置分布熱點(diǎn)圖", "數(shù)據(jù)來(lái)源：貓眼，F(xiàn)ly采集", title_color="#FFF", title_pos="center", width="100%", height=600, background_color="#404A59")

  attr1, value1 = geo1.cast(data)

  geo1.add("", attr1, value1, type="heatmap", visual_range=[0, 1000], visual_text_color="#FFF", symbol_size=15, is_visualmap=True, is_piecewise=False, visual_split_number=10)
  geo1.render("files/無(wú)名之輩-觀眾位置熱點(diǎn)圖.html")

  # 2 位置圖
  geo2 = Geo("《無(wú)名之輩》觀眾位置分布", "數(shù)據(jù)來(lái)源：貓眼，F(xiàn)ly采集", title_color="#FFF", title_pos="center", width="100%", height=600,
     background_color="#404A59")

  attr2, value2 = geo1.cast(data)
  geo2.add("", attr2, value2, visual_range=[0, 1000], visual_text_color="#FFF", symbol_size=15,
    is_visualmap=True, is_piecewise=False, visual_split_number=10)
  geo2.render("files/無(wú)名之輩-觀眾位置圖.html")

  # 3、top20 柱狀圖
  data_top20 = data[:20]
  bar = Bar("《無(wú)名之輩》觀眾來(lái)源排行 TOP20", "數(shù)據(jù)來(lái)源：貓眼，F(xiàn)ly采集", title_pos="center", width="100%", height=600)
  attr, value = bar.cast(data_top20)
  bar.add('', attr, value, is_visualmap=True, visual_range=[0, 3500], visual_text_color="#FFF", is_more_utils=True, is_label_show=True)
  bar.render("files/無(wú)名之輩-觀眾來(lái)源top20.html")

  print("圖表生成完成")

 def createWordCloud(self):
  """生成評(píng)論詞云"""
  comments = self.readAllComments() # 19185

  # 使用 jieba 分詞
  commens_split = jieba.cut(str(comments), cut_all=False)
  words = ''.join(commens_split)

  # 給詞庫(kù)添加停止詞
  stopwords = STOPWORDS.copy()
  stopwords.add("電影")
  stopwords.add("一部")
  stopwords.add("無(wú)名之輩")
  stopwords.add("一部")
  stopwords.add("一個(gè)")
  stopwords.add("有點(diǎn)")
  stopwords.add("覺(jué)得")

  # 加載背景圖片
  bg_image = plt.imread("files/2048_bg.png")

  # 初始化 WordCloud
  wc = WordCloud(width=1200, height=600, background_color='#FFF', mask=bg_image, font_path='C:/Windows/Fonts/STFANGSO.ttf', stopwords=stopwords, max_font_size=400, random_state=50)

  # 生成，顯示圖片
  wc.generate_from_text(words)
  plt.imshow(wc)
  plt.axis('off')
  plt.show()



if __name__ == "__main__":
 demo = ACoolFishAnalysis()
 demo.createWordCloud()