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
|
from random import randint
from urllib.parse import unquote,quote,parse_qs
import requests
import urllib.request
import json
import time as t
import datetime
import zlib
import re
import xml.etree.ElementTree as ET
import oss2
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360SE',
}
def get_response_iqiyi(url):
req = urllib.request.Request(url)
req.add_header("User-Agent",
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36")
response = urllib.request.urlopen(req).read()
return response
def get_response(url):
response = requests.get(url)
response.encoding = 'utf-8'
return response.text
def judgeIllegalChar(str):
illegal = False
for char in ["<", ">", "&", "\u0000", "\b"]:
if char in str:
illegal = True
break
return illegal
def make_response_head():
return '<?xml version="1.0" encoding="UTF-8"?>\n<i>\n'
def make_response_foot():
return '</i>'
def make_response_body(timepoint, content, ct=1, size=20, color=16777215,
unixtime=int(t.mktime(datetime.datetime.now().timetuple())), uid=0):
return '\t<d p="{},{},{},{},{},0,{},26732601000067074">{}</d>\n'.format(timepoint, ct, size, color, unixtime, uid,
content)
def mgtv(url):
cid = url.split('/')[4]
vid = url.split('/')[5].split('?')[0].strip('.html')
title = re.search(r'partName:"(.*?)",', get_response(url))
if title is not None:
title = title.group(1)
else:
title = 'Unknow'
contents = set()
ret = make_response_head()
time = 0
total = 0
cnt = 0
while True:
result = get_response('https://galaxy.bz.mgtv.com/rdbarrage?vid=' + vid + '&cid=' + cid + '&time=' + str(time))
danmu = json.loads(result)
if danmu['data']['items'] == None:
break
for j in danmu['data']['items']:
total += 1
if judgeIllegalChar(j['content']):
continue
timepoint = j['time'] / 1000
uid = j['uid']
content = j['content']
if content not in contents:
cnt += 1
contents.add(content)
ret += make_response_body(timepoint=timepoint, content=content, uid=uid)
time = danmu['data']['next']
ret += make_response_foot()
print("Download {} danmakus, Select {} danmakus\nfinish.".format(total, cnt))
return [title, ret]
def tencentvideo(url):
video_info = json.loads(
str([s for s in get_response(url).split('\n') if 'VIDEO_INFO' in str(s)]).strip('[\'var VIDEO_INFO = ').strip(
'\']'))
duration = video_info['duration']
title = video_info['title']
vid = video_info['vid']
targetid = json.loads(get_response('http://bullet.video.qq.com/fcgi-bin/target/regist?otype=json&vid=' + vid).strip(
'QZOutputJson=').strip(';'))['targetid']
contents = set()
ret = make_response_head()
total = 0
cnt = 0
for i in range(int(duration) // 30 + 1):
timestamp = i * 30
danmu = json.loads(
get_response('http://mfm.video.qq.com/danmu?timestamp=' + str(timestamp) + '&target_id=' + targetid),
strict=False)
for j in danmu['comments']:
total += 1
if judgeIllegalChar(j['content']):
continue
timepoint = j['timepoint']
ct = 1
size = 20
if "color" in j["content_style"]:
content_style = json.loads(j["content_style"])
color = int(content_style["color"], 16)
else:
color = 16777215
unixtime = int(t.mktime(datetime.datetime.now().timetuple()))
content = j['content']
if content not in contents:
cnt += 1
contents.add(content)
ret += '\t<d p="{},{},{},{},{},0,0,26732601000067074">{}</d>\n'.format(timepoint, ct, size, color,
unixtime, content)
ret += make_response_foot()
print("Download {} danmakus, Select {} danmakus\nfinish.".format(total, cnt))
return [title, ret]
def youku(url):
res = get_response(url)
title = re.search(r'<title>(.*)</title>', res).group(1).split('—')[0]
iid = re.search(r'videoId: \'(\d*)\'', res).group(1)
duration = float(re.search(r'seconds: \'(.*)\',', res).group(1))
contents = set()
total = 0
cnt = 0
ret = make_response_head()
for mat in range(int(duration) // 60 + 1):
response = get_response('https://service.danmu.youku.com/list?mat=' + str(mat) + '&ct=1001&iid=' + iid)
danmu = json.loads(response)
for i in range(len(danmu["result"])):
total += 1
if judgeIllegalChar(danmu["result"][i]["content"]):
continue
playat = danmu["result"][i]["playat"] / 1000
if "color" in danmu["result"][i]["propertis"]:
propertis = json.loads(danmu["result"][i]["propertis"])
color = propertis["color"]
else:
color = 16777215
content = danmu["result"][i]["content"]
if content not in contents:
contents.add(content)
cnt += 1
ret += make_response_body(timepoint=playat, color=color, content=content)
ret += make_response_foot()
print("Download {} danmakus, Select {} danmakus\nfinish.".format(total, cnt))
return [title, ret]
def iqiyi(url):
ret = get_response(url)
return ['iqiyi',ret]
page_info = json.loads(re.search(r"page-info='(.*)' :video-info=", get_response(url)).group(1))
duration_str = page_info['duration'].split(':')
duration = 0
for i in range(len(duration_str) - 1):
duration = (duration + int(duration_str[i])) * 60
duration = duration + int(duration_str[-1])
title = page_info['tvName']
albumid = page_info['albumId']
tvid = page_info['tvId']
categoryid = page_info['cid']
page = duration // (60 * 5) + 1
contents = set()
total = 0
cnt = 0
ret = make_response_head()
for i in range(duration // (60 * 5) + 1):
dec = zlib.decompressobj(32 + zlib.MAX_WBITS)
b = dec.decompress(get_response_iqiyi(
'http://cmts.iqiyi.com/bullet/' + str(tvid)[-4:-2] + '/' + str(tvid)[-2:] + '/' + str(tvid) + '_300_' + str(
i + 1) + '.z?rn=0.' + ''.join(["%s" % randint(0, 9) for num in range(0,
16)]) + '&business=danmu&is_iqiyi=true&is_video_page=true&tvid=' + str(
tvid) + '&albumid=' + str(albumid) + '&categoryid=' + str(categoryid) + '&qypid=01010021010000000000'))
root = ET.fromstring(b.decode("utf-8"))
for bulletInfo in root.iter('bulletInfo'):
total += 1
timepoint = bulletInfo[3].text
color = int(bulletInfo[5].text, 16)
content = bulletInfo[1].text
size = bulletInfo[4].text
if content not in contents:
cnt += 1
contents.add(content)
ret += make_response_body(timepoint=timepoint, color=color, content=content, size=size)
ret += make_response_foot()
print("Download {} danmakus, Select {} danmakus\nfinish.".format(total, cnt))
return [title, ret]
def save2oss(title, xml, download):
url = "XML/" + title + ".xml"
auth = oss2.Auth('******', '******')
endpoint_internal = 'oss-cn-******-internal.aliyuncs.com'
endpoint = 'oss-cn-******.aliyuncs.com'
bucketName = '****'
bucket = oss2.Bucket(auth, endpoint, bucketName)
headers = {}
if (download):
headers['Content-Type']='application/force-download'
else:
headers['Content-Type']='application/xml'
result = bucket.put_object(url, xml,headers=headers)
print('Upload URL:{}\tHTTP status: {}'.format(url, result.status))
return unquote(bucket.sign_url('GET', url, 120),'utf-8')
def bilibili(url):
text = get_response(url)
keyStr = re.findall(r'"cid":[\d]*', text)
if not keyStr:
keyStr = re.findall(r'cid=[\d]*', text)
key = eval(keyStr[0].split('=')[1])
else:
key = eval(keyStr[0].split(':')[1])
commentUrl = 'https://comment.bilibili.com/' + str(key) + '.xml'
return commentUrl
def build_response(url,download):
if url.find('mgtv.com') >= 0:
[title, ret] = mgtv(url)
elif url.find('qq.com') >= 0:
[title, ret] = tencentvideo(url)
elif url.find('youku.com') >= 0:
[title, ret] = youku(url)
elif url.find('iqiyi.com') >= 0:
[title, ret] = iqiyi(url)
elif url.find('bilibili.com') >= 0:
return bilibili(url)
else:
return None
return save2oss(title, ret, download)
def handler(environ, start_response):
if 'QUERY_STRING' not in environ:
status = '200 OK'
response_headers = [('Content-type', 'text/html; charset=UTF-8')]
with open("index.html", "r", encoding="utf-8") as f:
ret = f.read()
else:
query_string = environ['QUERY_STRING']
params = parse_qs(query_string)
download = params.get('download',['off'])[0]
download = (download == 'on')
url = unquote(params['url'][0], 'utf-8')
returl = build_response(url,download)
if returl is not None:
status = '302 Found'
response_headers = [('Location', quote(returl,safe='/:?&='))]
ret = ''
else:
status = '200 OK'
response_headers = [('Content-type', 'text/html; charset=UTF-8')]
ret = "不支持的视频网址"
start_response(status, response_headers)
return [ret.encode('utf8')]
|
