-
Notifications
You must be signed in to change notification settings - Fork 13
/
fox.py
325 lines (231 loc) · 8.68 KB
/
fox.py
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
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
import os
import re
import requests
from bs4 import BeautifulSoup
import json
class foxExtractor(object):
"""docstring for foxExtractor"""
def __init__(self, url, testMode):
print("Detected FOX NOW\nProcessing....\n")
self.loginRequired = False
self.urlName = url
self.debug = True
self.testMode = testMode
self.requestsFileName = "iDoNotExistDefinitelyOnThisComputerFolder.html"
self.showId = ""
self.showName = ""
self.videoGuid = ""
self.subtitleServer = "http://static-media.fox.com/cc/"
self.fileExtension = [".srt", ".dfxp"]
pass
def getSubtitles(self):
"""
The main function which uses helper functions to get the subtitles
"""
self.createSoupObject()
self.getTitle()
if self.debug:
print(self.title)
self.contentID = self.getContentID1(self.urlName) # Method-1
try:
self.contentID = int(self.contentID)
except:
print("Trying an alternative method to fetch Content ID")
self.contentID = self.getContentID2() # Method-2
try:
self.contentID = int(self.contentID)
except:
print("Unable to fetch the contentID.")
self.deleteUnnecessaryfiles()
return 0
if self.debug:
print(self.contentID)
jsonString = self.getShowJson()
if self.debug:
print(jsonString)
if not self.standardCheck(jsonString):
return 0
self.getShowDetails(jsonString)
if self.debug:
print(self.showId)
print(self.showName)
print(self.videoGuid)
if not self.standardCheck(self.showId, self.showName, self.videoGuid):
return 0
CaptionList = self.getSubtitleUrl()
if self.debug:
print(CaptionList)
for link in CaptionList:
returnValue = self.downloadTranscript(link)
if returnValue:
break
self.deleteUnnecessaryfiles()
return returnValue
def createSoupObject(self):
requestObject = requests.get(self.urlName)
# fileHandler = open("requests.txt", "w")
# fileHandler.write(requestObject.text)
# fileHandler.close()
self.soupObject = BeautifulSoup(
requestObject.text, "lxml", from_encoding="utf8")
# soupObject1 = BeautifulSoup(requestObject.text,"lxml")
# print(self.soupObject.original_encoding)
fh = open(self.requestsFileName, "w")
fh.write(str(self.soupObject))
fh.close()
pass
def getContentID1(self, url):
"""This is one of the methodologies to get the content ID. If this fails the alternative method will be called
The URL follows a specific standard throughout.
http://www.fox.com/watch/684171331973/7684520448
We need to split and return "684171331973"
"""
contentId = ''
try:
searchStringList = ["watch/"]
juknkData, episodeName, IDContainer = url.partition(
searchStringList[0])
contentId, Slash, Junk = IDContainer.partition("/")
except:
pass
return contentId
def getContentID2(self):
"""
This is the alternative method to obtain the contentID.
<meta content="http://www.fox.com/watch/681382467805/7683748608" property="og:url"/>
Obtained from the SOUP.
"""
contentId = ''
try:
UrlObj = self.soupObject.find("meta", attrs={"property": "og:url"})
Url = UrlObj['content']
contentId = self.getContentID1(Url)
except:
pass
return contentId
pass
def getShowJson(self):
"""
The required script content looks like this-
jQuery.extend(Drupal.settings, {"":...............});
1) We add everything to a new string after encountering the first "{".
2) Remove the last parantheses and the semi-colon to create a valid JSON. ---- ');'
"""
scripts = self.soupObject.findAll("script")
rawScript = ""
for strs in scripts:
if strs.string is not None:
if "showid" in strs.string:
rawScript = strs.string
addState = False
jsonString = ''
for i in rawScript:
if i == "{" and addState is False:
addState = True
if addState is True:
jsonString += i
jsonString = jsonString.replace(");", "")
return jsonString
pass
def getShowDetails(self, jsonString):
"""
The json content looks like this -
{"foxProfileContinueWatching":{"showid":"empire","showname":"Empire"},..............
"foxAdobePassProvider": {......,"videoGUID":"2AYB18"}}
"""
try:
IndexingParameters = [
["foxProfileContinueWatching", "showid", "showname"],
["foxAdobePassProvider", "videoGUID"],
]
parsedJsonObject = json.loads(jsonString)
self.showId = parsedJsonObject[
IndexingParameters[0][0]][IndexingParameters[0][1]]
self.showName = parsedJsonObject[
IndexingParameters[0][0]][IndexingParameters[0][2]]
self.videoGuid = parsedJsonObject[
IndexingParameters[1][0]][IndexingParameters[1][1]]
except:
print("Unable to parse Json. Please report.")
pass
pass
def getSubtitleUrl(self):
"""
Sample Subtitle Link -
http://static-media.fox.com/cc/sleepy-hollow/SleepyHollow_3AWL18_660599363942.srt
http://static-media.fox.com/cc/sleepy-hollow/SleepyHollow_3AWL18_660599363942.dfxp
The standard followed is -
http://static-media.fox.com/cc/[showid]/showname_videoGUID_contentID.srt
OR
http://static-media.fox.com/cc/[showid]/showname_videoGUID_contentID.dfxp
Some Subtitle URL's follow this standard -
http://static-media.fox.com/cc/[showid]/showname_videoGUID.dfxp
http://static-media.fox.com/cc/[showid]/showname_videoGUID.srt
So we store both URL's and check both
"""
SubsUrl = self.subtitleServer
SecondarySubsUrl = ''
self.showName = self.processShowName(self.showName)
SubsUrl += str(self.showId)
SubsUrl += "/"
SubsUrl += str(self.showName)
SubsUrl += "_"
SubsUrl += str(self.videoGuid)
SecondarySubsUrl = SubsUrl
SubsUrl += "_"
SubsUrl += str(self.contentID)
SubsUrl += self.fileExtension[0]
SecondarySubsUrl += self.fileExtension[0]
return [SubsUrl, SecondarySubsUrl]
def processShowName(self, name):
"""
Removes white spaces
"""
name = name.replace(" ", "")
return name
def downloadTranscript(self, SubsLink):
"""
This function fetches the captions and writes them into a file in VTT format
"""
try:
subRequestObject = requests.get(SubsLink)
subRequestObject.encoding = 'utf-8'
# print(subRequestObject.text)
if subRequestObject.status_code >= 400:
# Deliberate error to exit.
s = int("deliberateError")
subsFileHandler = open(self.title + self.fileExtension[0], "w")
print("Creating ~ '%s%s' ..." %
(self.title, self.fileExtension[0]))
subsFileHandler.write(subRequestObject.text)
subsFileHandler.close()
return 1
except:
return 0
pass
def getTitle(self):
"""
This function returns the title of the video. This is also used for naming the file.
<title>Watch New Girl Online: Episode 21, Season 5 on FOX</title> --> Extracting the value from here
"""
# print(self.soupObject.title.string)
try:
self.title = self.soupObject.title.string.strip()
if not self.title:
s = int("deliberateError")
except:
self.title = "DownloadedFOXNowSubtitles"
pass
def deleteUnnecessaryfiles(self):
if not self.debug:
try:
os.remove(self.requestsFileName)
except:
pass
def standardCheck(self, *variablesToCheck):
for variables in variablesToCheck:
if not variables:
print("Unable to fetch the subtitles.")
self.deleteUnnecessaryfiles()
return 0
return 1