微博[1543]&nbsp

regx = re.findall(pattern, wb_num, re.S | re.M) # 只要数字（字符）

for value in regx:

num_wb = int(value)

break

self.Number = num_wb

# 关注数

str_gz = selector.xpath("//div[@class='tip2']/a/text()")[0]

regx = re.findall(pattern, str_gz, re.M)

self.Guanzhu = int(regx[0])

# 粉丝数

str_fs = selector.xpath("//div[@class='tip2']/a/text()")[1]

regx = re.findall(pattern, str_fs, re.M)

self.fans = int(regx[0])

# 获取"长微博"全部文字内容

def GetLong(self, weibo_link):

html = requests.get(weibo_link, cookies=self.cookie).content

selector = etree.HTML(html)

info = selector.xpath("//div[@class='c']")[1]

wb_content = info.xpath("div/span[@class='ctt']")[0].xpath(

"string(.)").replace(u"\u200b", "").encode(sys.stdout.encoding, "ignore").decode(

sys.stdout.encoding)

return wb_content

# 获取转发微博信息

def GetZhuanfa(self, is_retweet, info, wb_content):

original_user = is_retweet[0].xpath("a/text()")

if not original_user:

wb_content = u"转发微博已被删除"

return wb_content

else:

original_user = original_user[0]

retweet_reason = info.xpath("div")[-1].xpath("string(.)").replace(u"\u200b", "").encode(

sys.stdout.encoding, "ignore").decode(

sys.stdout.encoding)

retweet_reason = retweet_reason[:retweet_reason.rindex(u"赞")]

wb_content = (retweet_reason + "\n" + u"原始用户: " +

original_user + "\n" + u"转发内容: " + wb_content)

return wb_content

#一个界面展示一条微博的发布时间、点赞数、转发数、评论数

def weibo_para(self):

url = "https://weibo.cn/u/%d?&page=1" % (self.Id)

html = requests.get(url, cookies=self.cookie).content

selector = etree.HTML(html)

if selector.xpath("//input[@name='mp']") == []:

page_num = 1

else:

page_num = (int)(selector.xpath(

"//input[@name='mp']")[0].attrib["value"])

pattern = r"\d+\.?\d*"

for page in range(1, page_num + 1):

url2 = "https://weibo.cn/u/%d?&page=%d" % (

self.Id, page)

html2 = requests.get(url2, cookies=self.cookie).content

selector2 = etree.HTML(html2)

info = selector2.xpath("//div[@class='c']")

is_empty = info[0].xpath("div/span[@class='ctt']")

if is_empty:

for i in range(0, len(info) - 2):

# 微博内容

str_t = info[i].xpath("div/span[@class='ctt']")

Content = str_t[0].xpath("string(.)").replace(u"\u200b", "").encode(

sys.stdout.encoding, "ignore").decode(

sys.stdout.encoding)

Content = Content[:-1]

weibo_Id = info[i].xpath("@id")[0][2:]

a_link = info[i].xpath(

"div/span[@class='ctt']/a")

is_retweet = info[i].xpath("div/span[@class='cmt']")

if a_link:

if a_link[-1].xpath("text()")[0] == u"全文":

weibo_link = "https://weibo.cn/comment/" + weibo_Id

wb_content = self.GetLong(weibo_link)

if wb_content:

if not is_retweet:

wb_content = wb_content[1:]

Content = wb_content

if is_retweet:

Content = self.GetZhuanfa(

is_retweet, info[i], Content)

self.Content.append(Content)

# 微博发布时间

str_time = info[i].xpath("div/span[@class='ct']")

str_time = str_time[0].xpath("string(.)").encode(sys.stdout.encoding, "ignore").decode(

sys.stdout.encoding)

Time = str_time.split(u'来自')[0]

if u"刚刚" in Time:

Time = datetime.now().strftime('%Y-%m-%d %H:%M')

elif u"分钟" in Time:

minute = Time[:Time.find(u"分钟")]

minute = timedelta(minutes=int(minute))

Time = (datetime.now() - minute).strftime("%Y-%m-%d %H:%M")

elif u"今天" in Time:

today = datetime.now().strftime("%Y-%m-%d")

time = Time[3:]

Time = today + " " + time

elif u"月" in Time:

year = datetime.now().strftime("%Y")

month = Time[0:2]

day = Time[3:5]

time = Time[7:12]

Time = (

year + "-" + month + "-" + day + " " + time)

else:

Time = Time[:16]

self.Time.append(Time)

str_footer = info[i].xpath("div")[-1]

str_footer = str_footer.xpath("string(.)").encode(

sys.stdout.encoding, "ignore").decode(sys.stdout.encoding)

str_footer = str_footer[str_footer.rfind(u'赞'):]

regx = re.findall(pattern, str_footer, re.M)

# 微博发布工具

if len(str_time.split(u'来自')) > 1:

publish_tool = str_time.split(u'来自')[1]

else:

publish_tool = u"无"

self.publish_tool.append(publish_tool)

str_footer = info[i].xpath("div")[-1]

str_footer = str_footer.xpath("string(.)").encode(

sys.stdout.encoding, "ignore").decode(sys.stdout.encoding)

str_footer = str_footer[str_footer.rfind(u'赞'):]

guid = re.findall(pattern, str_footer, re.M)

# 点赞数

star = int(regx[0])

self.star.append(star)

# 转发数

Zhuanfa = int(regx[1])

self.Zhuanfa.append(Zhuanfa)

# 评论数

Pinglun = int(regx[2])

self.Pinglun.append(Pinglun)

self.number1 += 1

# 将爬取的信息写入文件--------------------------------------------------------------------------

def write_txt(self):

try:

contents_header = u"\n\n微博内容: \n"

contents = (u"用户信息\n用户昵称：" + self.username +

u"\n用户Id: " + str(self.Id) +

u"\n微博数: " + str(self.Number) +

u"\n关注数: " + str(self.Guanzhu) +

u"\n粉丝数: " + str(self.fans) + contents_header + '\n')

for i in range(1, self.number1 + 1):

text = (str(i) + ":" + self.Content[i - 1] + "\n" +

u"发布工具: " + self.publish_tool[i - 1] + "\n" +

u"发布时间: " + self.Time[i - 1] + "\n" +

u"点赞数: " + str(self.star[i - 1]) +

u"转发数: " + str(self.Zhuanfa[i - 1]) +

u"评论数: " + str(self.Pinglun[i - 1]) + "\n\n")

contents = contents + text

global file_path

f = open(file_path, "wb")

f.write(contents.encode(sys.stdout.encoding))

f.close()

except Exception as e:

print("Error: ", e)

traceback.print_exc()

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

测试函数部分

def main():

weibo = Wb()

weibo.Operate()

weibo.MainLoop()

if __name__ == "__main__":

main()

1

2

3

4

5

6

7

数据分析部分：用matplotlib制图，只是粗浅学了一些，所以画的不够精美，数据过少，分析的可能有点问题，emmm，一共画了四张图， “2017-2018微博转发/点赞量折线统计图”、 ‘原创微博与转发微博统计图’ 、 ‘微博发布工具统计图’、 ‘微博使用心情统计图’

import re

import numpy as np

import matplotlib.pyplot as plt

import matplotlib.dates as mdate

from matplotlib import font_manager as fm

import time

from datetime import datetime

import webbrowser

class analysis(object):

def __init__(self,file_name,number):

self.file_name = file_name

self.number = number

self.X_data = []

self.Y1_data = []

self.Y_data = []

self.str = ""

## 折线图展示窗口

def analyse_Zhexian(self):

pattern = re.compile(r'转发数: \d+') # 查找数字

pattern1 = re.compile(r'\d+')#匹配转发数或者评论数的数字字符

pattern2 = re.compile(r'发布时间: (\d{4}-\d{1,2}-\d{1,2}\s\d{1,2}:\d{1,2})')#提取时间

pattern3 = re.compile(r'.*2016.*')

pattern4 = re.compile(r'点赞数: \d+')

with open(self.file_name,encoding = "utf-8") as f:

str = f.read()

# 用正则表达式提取所需数据

result = pattern.findall(str)

ls3 = ''.join(result)#拼接成一个字符串

Result = pattern1.findall(ls3)#把所有数字提取完毕

Num_Zhuanfa = [ int(x) for x in Result ] # y轴1

result1 = pattern4.findall(str)

ls1 = ''.join(result1)

Result1 = pattern1.findall(ls1)

Num_Dianzan = [int(x) for x in Result1] # y轴2

# 将x轴数据转化为datetime 类型

Num_Zhuanfa_time = pattern2.findall(str)

for i in range(0,len(Num_Zhuanfa_time)):

if pattern3.findall(Num_Zhuanfa_time[i]):

stop = i # 用stop记录2016年的最后一条微博

break

#只选择2017-2018年两年的数据，因为微博数太多，横轴日期占比太大，matplotlib的横坐标显示不完全，中间会有大量重叠，这里数据分析的算法并不好，结果出来还是会有很大重叠，如果有更好的办法请大佬指教

Num_Zhuanfa = Num_Zhuanfa[0:stop:1]

Num_Zhuanfa_time = Num_Zhuanfa_time[0:stop:1]

Num_Dianzan = Num_Dianzan[0:stop:1]

# 数据除以1000，画图更美观

for i in range(0,len(Num_Zhuanfa)):

Num_Zhuanfa[i] = Num_Zhuanfa[i] /1000

for i in range(0,len(Num_Dianzan)):

Num_Dianzan[i] = Num_Dianzan[i] /1000

#将时间转化为时间戳再转化为datetime类型

aa=[time.strptime(i, "%Y-%m-%d %H:%M") for i in Num_Zhuanfa_time]

timeStamp = [int(time.mktime(a)) for a in aa]

Num_Zhuanfa_time=[datetime.fromtimestamp(k) for k in timeStamp]

# 处理数据量过多的问题

number = len(Num_Zhuanfa)

Group = int(0.18 * number)

k = number // Group # 数据太多，这里只要15%的数据，分组，每组随机选一个作为代表数据

for i in range(0,Group):

self.X_data.append(Num_Zhuanfa_time[i*k])

self.Y_data.append(Num_Zhuanfa[i*k])

self.Y1_data.append(Num_Dianzan[i*k])

# 绘制两条折线

fig1 = plt.figure(figsize=(8,5))

plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签

ax1 = fig1.add_subplot(1,1,1)

ax1.xaxis.set_major_formatter(mdate.DateFormatter('%Y-%m-%d %H-%M'))#设置时间标签显示格式

plt.xticks(self.X_data,rotation=90)#竖着输出时间

plt.yticks(np.linspace(0,5000,5,endpoint=True))

plt.title(u"2017-2018微博转发/点赞量折线图",color="black")

plt.plot(self.X_data,self.Y_data,"o-",color='skyblue',label="转发量",markersize=1.5) #折线

plt.plot(self.X_data,self.Y1_data,"o-",color='pink',label="点赞量",markersize=1.5)

plt.xlabel("发布时间")

plt.ylabel("数量(千/条)")

plt.legend() # 显示标签

plt.show()

def analyse_YC(self):

pattern = re.compile(r'转发理由')

with open(self.file_name,encoding = "utf-8") as f:

str = f.read()

Zhuanfa = pattern.findall(str)

Number_Zhuanfa = int(len(Zhuanfa))

Yuanchuang = self.number - Number_Zhuanfa

plt.rcParams['font.sans-serif'] = ['SimHei']

labels = ['转发微博','原创微博']

sizes = [Number_Zhuanfa,Yuanchuang]

explode= (0.1,0)

plt.pie(sizes,explode=explode,labels=labels,autopct='%1.1f%%',shadow=False,startangle=150)

plt.title(u"原创与转发微博量",color="black")

plt.show()

def analyse_GJ(self):

pattern = re.compile(r'发布工具: (.*)\n发布时间')

with open(self.file_name,encoding = "utf-8") as f:

str = f.read()

number_GJ = pattern.findall(str)

#print(number_GJ)

gongju = dict()

for i in number_GJ:

name = i

if name in gongju:

gongju[name]+=1

else:

gongju[name]=1

# 少于10的记录舍去

for key in list(gongju.keys()):

if gongju[key]<=10:

del gongju[key]

labels = list(gongju.keys())

sizes = list(gongju.values())

plt.rcParams['font.sans-serif'] = ['SimHei']

plt.pie(sizes,labels=labels,autopct='%1.1f%%',shadow=True,startangle=150)

plt.title(u"微博发布工具统计",color="black")

plt.show()

def analyse_XQ(self):

pattern = re.compile(r'\[(.{1,4})\].*\[(.{1,4})\]')

with open(self.file_name,encoding = "utf-8") as f:

str = f.read()

number_XQ = pattern.findall(str)

# print(number_XQ)

a=[]

for i in range(0,len(number_XQ)):

for j in (range(0,len(number_XQ[i]))):

a.append(number_XQ[i][j])

biaoqing = dict()

for i in a:

name = i

if name in biaoqing:

biaoqing[name]+=1

else:

biaoqing[name]=1

for key in list(biaoqing.keys()):

if biaoqing[key] <= 2:

del biaoqing[key]

labels = list(biaoqing.keys())

sizes = list(biaoqing.values())

fig1, ax1 = plt.subplots(http://www.my516.com)

patches, texts, autotexts = ax1.pie(sizes, labels=labels, autopct='%1.0f%%',

shadow=False, startangle=170)

ax1.axis('equal')

#重新设置字体大小

plt.rcParams['font.sans-serif'] = ['SimHei']

proptease = fm.FontProperties()

proptease.set_size('small')

plt.title(u"微博表情使用次数",color="black")

plt.setp(autotexts, fontproperties=proptease)

plt.setp(texts, fontproperties=proptease)

plt.show()

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

python程序打包

#在cmd下安装pyinstaller

pip install pyinstaller

#打包成一个可执行文件 -F (注意将cmd窗口切换至文件保存的路径下)

pyinstaller -F filename.py

1

2

3

4

5

本篇只适合新手简单学习，笔者也刚学，加上复习周，后期会逐渐完善，毕竟UI写的太丑了 ！

另：关于获取本地用户cookie和微博账号的id操作比较简单在此不再做详细解释。如果程序跑不出来相信我一定是cookie问题

---------------------