Python實現微信好友數據爬取及分析

itchat.auto_login(hotReload = True) 
friends = itchat.get_friends(update = True)

def analyseSex(firends): 
  sexs = list(map(lambda x:x['Sex'],friends[1:])) 
 counts = list(map(lambda x:x[1],Counter(sexs).items())) 
 labels = ['Unknow','Male','Female'] 
 colors = ['red','yellowgreen','lightskyblue'] 
 plt.figure(figsize=(8,5), dpi=80) 
 plt.axes(aspect=1) 
 plt.pie(counts, #性別統計結果 
   labels=labels, #性別展示標簽 
   colors=colors, #餅圖區域配色 
   labeldistance = 1.1, #標簽距離圓點距離 
   autopct = '%3.1f%%', #餅圖區域文本格式 
   shadow = False, #餅圖是否顯示陰影 
   startangle = 90, #餅圖起始角度 
   pctdistance = 0.6 #餅圖區域文本距離圓點距離 
 ) 
 plt.legend(loc='upper right',) 
 plt.title(u'%s的微信好友性別組成' % friends[0]['NickName']) 
 plt.show()

def analyseHeadImage(frineds): 
 # Init Path 
 basePath = os.path.abspath('.') 
 baseFolder = basePath + '\\HeadImages\\'
 if(os.path.exists(baseFolder) == False): 
  os.makedirs(baseFolder)  
 # Analyse Images 
 faceApi = FaceAPI() 
 use_face = 0
 not_use_face = 0
 image_tags = '' 
 for index in range(1,len(friends)): 
  friend = friends[index] 
  # Save HeadImages 
  imgFile = baseFolder + '\\Image%s.jpg' % str(index) 
  imgData = itchat.get_head_img(userName = friend['UserName']) 
  if(os.path.exists(imgFile) == False): 
   with open(imgFile,'wb') as file: 
    file.write(imgData)   
  # Detect Faces 
  time.sleep(1) 
  result = faceApi.detectFace(imgFile) 
  if result == True: 
   use_face += 1
  else: 
   not_use_face += 1  
  # Extract Tags 
  result = faceApi.extractTags(imgFile) 
  image_tags += ','.join(list(map(lambda x:x['tag_name'],result)))  
 labels = [u'使用人臉頭像',u'不使用人臉頭像'] 
 counts = [use_face,not_use_face] 
 colors = ['red','yellowgreen','lightskyblue'] 
 plt.figure(figsize=(8,5), dpi=80) 
 plt.axes(aspect=1) 
 plt.pie(counts, #性別統計結果 
   labels=labels, #性別展示標簽 
   colors=colors, #餅圖區域配色 
   labeldistance = 1.1, #標簽距離圓點距離 
   autopct = '%3.1f%%', #餅圖區域文本格式 
   shadow = False, #餅圖是否顯示陰影 
   startangle = 90, #餅圖起始角度 
   pctdistance = 0.6 #餅圖區域文本距離圓點距離 
 ) 
 plt.legend(loc='upper right',) 
 plt.title(u'%s的微信好友使用人臉頭像情況' % friends[0]['NickName']) 
 plt.show()  
 image_tags = image_tags.encode('iso8859-1').decode('utf-8') 
 back_coloring = np.array(Image.open('face.jpg')) 
 wordcloud = WordCloud( 
  font_path='simfang.ttf', 
  background_color="white", 
  max_words=1200, 
  mask=back_coloring, 
  max_font_size=75, 
  random_state=45, 
  width=800, 
  height=480, 
  margin=15
 )  
 wordcloud.generate(image_tags) 
 plt.imshow(wordcloud) 
 plt.axis("off") 
 plt.show()

def analyseSignature(friends): 
 signatures = '' 
 emotions = [] 
 pattern = re.compile("1f\d.+") 
 for friend in friends: 
  signature = friend['Signature'] 
  if(signature != None): 
   signature = signature.strip().replace('span', '').replace('class', '').replace('emoji', '') 
   signature = re.sub(r'1f(\d.+)','',signature) 
   if(len(signature)>0): 
    nlp = SnowNLP(signature) 
    emotions.append(nlp.sentiments) 
    signatures += ' '.join(jieba.analyse.extract_tags(signature,5)) 
 with open('signatures.txt','wt',encoding='utf-8') as file: 
   file.write(signatures) 
 # Sinature WordCloud 
 back_coloring = np.array(Image.open('flower.jpg')) 
 wordcloud = WordCloud( 
  font_path='simfang.ttf', 
  background_color="white", 
  max_words=1200, 
  mask=back_coloring, 
  max_font_size=75, 
  random_state=45, 
  width=960, 
  height=720, 
  margin=15
 ) 
 wordcloud.generate(signatures) 
 plt.imshow(wordcloud) 
 plt.axis("off") 
 plt.show() 
 wordcloud.to_file('signatures.jpg') 
 # Signature Emotional Judgment 
 count_good = len(list(filter(lambda x:x>0.66,emotions))) 
 count_normal = len(list(filter(lambda x:x>=0.33 and x<=0.66,emotions))) 
 count_bad = len(list(filter(lambda x:x<0.33,emotions))) 
 labels = [u'負面消極',u'中性',u'正面積極'] 
 values = (count_bad,count_normal,count_good) 
 plt.rcParams['font.sans-serif'] = ['simHei'] 
 plt.rcParams['axes.unicode_minus'] = False
 plt.xlabel(u'情感判斷') 
 plt.ylabel(u'頻數') 
 plt.xticks(range(3),labels) 
 plt.legend(loc='upper right',) 
 plt.bar(range(3), values, color = 'rgb') 
 plt.title(u'%s的微信好友簽名信息情感分析' % friends[0]['NickName']) 
 plt.show()

def analyseLocation(friends): 
 headers = ['NickName','Province','City'] 
 with open('location.csv','w',encoding='utf-8',newline='',) as csvFile: 
  writer = csv.DictWriter(csvFile, headers) 
  writer.writeheader() 
  for friend in friends[1:]: 
   row = {} 
   row['NickName'] = friend['NickName'] 
   row['Province'] = friend['Province'] 
   row['City'] = friend['City'] 
   writer.writerow(row)