FilesExpand file tree

master

/

imdbScript.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

240 lines (179 loc) · 7.15 KB

master

/

imdbScript.py

Copy path

Top

File metadata and controls

• Code
• Blame

240 lines (179 loc) · 7.15 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

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

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

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

"""

@author: Manu kumar

"""

############################ IMPORTING PACKAGES ##########################

from bs4 import BeautifulSoup

from urllib.request import urlopen

from datetime import datetime

from datetime import date

import mysql.connector

import smtplib

from email.mime.multipart import MIMEMultipart

from email.mime.text import MIMEText

from email.mime.base import MIMEBase

from email import encoders

############################# MYSQL CONNECTION #####################

db = mysql.connector.connect(

host="localhost",

user="root",

passwd="root",

database="userShows"

)

#################################### CREATION OF DATABASE ###############################

cursor = db.cursor()

cursor.execute("CREATE DATABASE IF NOT EXISTS userShows")

sql = """CREATE TABLE IF NOT EXISTS ShowDetails (

Name VARCHAR(100),

Email_address VARCHAR(100),

TV_Series VARCHAR(1000)

)"""

cursor.execute(sql)

#################################### GETTING INPUTS FROM USER ####################################

Name_input = input("Input your name: ")

Email_address_input = input("Email address: ")

TV_Series_input = input("TV Series: ")

fromaddr = "imdbscriptManukumar@gmail.com"

toaddr = Email_address_input

############################### MAKING CHANGES IN DATABASE ###################################

try:

entry = ("INSERT INTO ShowDetails (Name, Email_address, TV_Series) VALUES (%s, %s, %s)")

val = (Name_input, Email_address_input, TV_Series_input)

# Execute the SQL command

cursor.execute(entry, val)

# Commit changes in the database

db.commit()

print("\nData stored into database")

except:

# Rollback in case there is any error

db.rollback()

# disconnect from server

db.close()

###################### OBTAINING CURRENT DATE #################################################

Status = []

Ser_inv_name = []

today = date.today()

today = str(today)

########################### WORKING ON INDIVIDUAL SERIES SEARCH #########################################

TV_Series = TV_Series_input.split(", ")

l = (len(TV_Series))

for indivSeries in TV_Series:

Ser_inv_name.append(indivSeries)

series_search = "+".join((indivSeries).split())

base_url = "https://www.imdb.com/search/title?title="

new_url = base_url+series_search+'&title_type=tv_series'

#base_url = "http://www.imdb.com/find?q="

#new_url = base_url+series_search+'&s=all'

####################### FETCHING URL SEARCH RESULTS #####################################

x = urlopen(new_url)

source = x.read()

#source = requests.get(new_url).text

soup = BeautifulSoup(source, "xml")

########################## FETCHING LINK OF A SPECIFIC SHOW ################################

res_url = soup.find('div', class_='lister-item mode-advanced')

res_url = res_url.find('div', class_='lister-item-content').h3.a

res_url = res_url.get('href')

base_res_url = "https://www.imdb.com"

showIMDBlink = base_res_url+res_url

####################### SCRAPPING OF DATA ###################################

y = urlopen(showIMDBlink)

source1 = y.read()

soupa = BeautifulSoup(source1, "xml")

first_link = soupa.find(id = "main_bottom", class_='main')

seasonNum = first_link.find('div', class_='seasons-and-year-nav')

currentSeason = seasonNum.find('a')

currentSeasonNum = currentSeason.text

############################ FETCHING LINK OF LATEST SEASON ##########################

season_url = seasonNum.find('a')

season_url = season_url.get('href')

season_url = season_url.replace("=tt", "&ref_=tt")

seasonIMDBlink = base_res_url+season_url

# print(seasonIMDBlink)

######################### SCRAPPING FROM LATEST SEASON #################################

z = urlopen(seasonIMDBlink)

source2 = z.read()

soupb = BeautifulSoup(source2, "xml")

################## Checking if the show has finished streaming all its episodes ###########

showOver = soupb.find('div', class_='subpage_title_block')

showOver = showOver.find('div', class_='parent').h3

showOver = showOver.find('span', class_='nobr').text.strip()

showOver1 = showOver.split("–")[1]

showOverYear = showOver1.strip(")")

if showOverYear != " ":

emailMsg = "Status: The show has finished streaming all its episodes."

Status.append(emailMsg)

# print(emailMsg)

####################### SHOW HAS NOT FINISHED STREAMING #######################################

else:

ans=[]

allD=[]

sizes=[]

episodeDates = soupb.find('div', class_='list detail eplist')

for epDates in episodeDates.find_all('div', {"class":"airdate"}):

epDates = epDates.text.strip()

epDates = epDates.replace(".", "")

sz = len(epDates)

sizes.append(len(epDates))

allD.append(epDates)

if((sz) > 4):

epDates = datetime.strptime(epDates, '%d %b %Y')

epDates = str(epDates)

epDates = datetime.strptime(epDates, '%Y-%m-%d %H:%M:%S').strftime('%Y-%m-%d')

ans.append(epDates)

n = len(ans)

###################################################################################################################################################

if((len(str(allD[0]))) == 4):

epDates = datetime.strptime(allD[0], '%Y')

epDates = str(epDates)

epDates = datetime.strptime(epDates, '%Y-%m-%d %H:%M:%S').strftime('%Y')

emailMsg = "Status: The next season begins in {0}.".format(epDates)

Status.append(emailMsg)

# print(emailMsg)

#####################################################################################################################################

else:

for i in range (0,n):

if(ans[i] > today and i<n):

break

else:

i+=1

if(i==n):

emailMsg = "Status: The show has finished streaming all its episodes."

Status.append(emailMsg)

# print(emailMsg)

else:

emailMsg = "Status: Next episode airs on {0}.".format(ans[i])

Status.append(emailMsg)

# print(emailMsg)

#print(Status)

#print(Ser_inv_name)

finalbody = []

finalPrintBody = []

body = "TV Series: "

space = " "

for j in range (0,l):

bodyprint = body + TV_Series[j]

finalbody.append(bodyprint)

j+=1

#print(finalbody)

for k in range (0, l):

finalPrintBody.append(finalbody[k])

finalPrintBody.append(Status[k])

finalPrintBody.append(space)

#print(*finalPrintBody,sep='\n')

msg = MIMEMultipart()

msg['From'] = fromaddr

msg['To'] = toaddr

msg['Subject'] = "Show Details"

body = ''

for row in finalPrintBody:

body += '%s\n' % row

msg.attach(MIMEText(body, 'plain'))

mail = smtplib.SMTP('smtp.gmail.com', 587)

mail.ehlo()

mail.starttls()

mail.ehlo()

mail.login(fromaddr, "manukumar")

text = msg.as_string()

mail.sendmail(fromaddr, toaddr, text)

mail.close()

print("\nEmail sent to the provided Email address")