首頁 探索 說明
註冊 登入
fengtao
/
spider
關註 1
讚好 0
派生 0
代碼 問題管理 0 合併請求 0 提交歷史 1 版本發佈 0 Wiki
瀏覽代碼

bug

fengtao 1 年之前
當前提交
fce6b0bedd
共有 7 個文件被更改，包括 2188 次插入 和 0 次删除
分割檢視 顯示文件統計
  1. 5 0
      cookie_test.txt
  2. 0 0
      db-mysql.err
  3. 93 0
      mysql.py
  4. 二進制
      mysql.pyc
  5. 1728 0
      nohup.out
  6. 222 0
      rov8.py
  7. 140 0
      taopp.py

+ 5 - 0
cookie_test.txt
查看文件 

@ -0,0 +1,5 @@
1 
# Netscape HTTP Cookie File
2 
# http://curl.haxx.se/rfc/cookie_spec.html
3 
# This is a generated file!  Do not edit.
4
5 
www.rov8.com	FALSE	/	FALSE		PHPSESSID	vnk5fkk4itkp4pbskehun8gkj1

+ 0 - 0
db-mysql.err
查看文件


+ 93 - 0
mysql.py
查看文件 

@ -0,0 +1,93 @@
1 
#!/usr/bin/env python
2 
# coding: utf-8
3
4 
import MySQLdb
5 
import time
6 
import sys
7 
reload(sys)
8 
sys.setdefaultencoding('utf8')
9
10 
class Mysql:
11 
    # 获取当前时间
12 
    def getCurrentTime(self):
13 
        return time.strftime('[%Y-%m-%d %H:%M:%S]', time.localtime(time.time()))
14 
    # 数据库初始化
15 
    def __init__(self):
16 
        try:
17 
	   #self.db =  MySQLdb.connect('127.0.0.1', 'flyer_user', 'Tu4a0X9hOPKz6jS!e', 'flyer_db', 22809)
18 
	    self.db =  MySQLdb.connect('rm-2zeqhsdou4zxl4914.mysql.rds.aliyuncs.com', 'flyer_user', 'GLZcMigd4VnsrmzNrOC1HGjv2eQzBqg3', 'flyer_db', 3306)
19 
            #self.db = MySQLdb.connect('localhost', 'flyer_user', 'Tu4a0X9hOPKz6jS!e', 'flyer_db', 22809,charset='utf8')
20 
            self.cur = self.db.cursor()
21 
        except MySQLdb.Error, e:
22 
            print self.getCurrentTime(), "连接数据库错误，原因%d: %s" % (e.args[0], e.args[1])
23
24 
    # 插入数据
25 
    def insertData(self, my_dict):
26 
        try:
27 
            self.db.set_character_set('utf8')
28 
            cols = ', '.join(my_dict.keys())
29 
            print cols
30 
            values = '","'.join(my_dict.values())
31 
            print values
32 
            sql = "INSERT INTO  versions_update_wechat (%s) VALUES (%s)" % (cols, '"' + values + '"')
33 
            try:
34 
                result = self.cur.execute(sql)
35 
                insert_id = self.db.insert_id()
36 
                self.db.commit()
37 
                # 判断是否执行成功
38 
                if result:
39 
                    return insert_id
40 
                else:
41 
                    return 0
42 
            except MySQLdb.Error, e:
43 
                # 发生错误时回滚
44 
                self.db.rollback()
45 
                # 主键唯一，无法插入
46 
                if "key 'PRIMARY'" in e.args[1]:
47 
                    print self.getCurrentTime(), "数据已存在，未插入数据"
48 
                else:
49 
                    print self.getCurrentTime(), "插入数据失败，原因 %d: %s" % (e.args[0], e.args[1])
50 
        except MySQLdb.Error, e:
51 
            print self.getCurrentTime(), "数据库错误，原因%d: %s" % (e.args[0], e.args[1])
52 
        # self.db.close
53
54 
    def dealData(self, my_dict):
55 
        """先从数据库中查询这个影片名的记录，如果没有直接插入；
56 
        接下来在判断从页面中获取的出字幕时间如果没有数据，直接pass，不做任何操作
57 
        有具体的字幕时间才进行更新操作"""
58 
        self.db.set_character_set('utf8')
59 
        filmTitile = my_dict.get('film_title')
60 
        captionTime = my_dict.get('caption_time')
61 
        result = self.findFilmByfilmTitle(filmTitile)
62 
        if len(result) == 0:
63 
            self.insertData(my_dict)
64 
            return
65 
        if captionTime.find("别着急") == 0:
66 
            pass
67 
        else:
68 
            self.updateData(my_dict)
69
70 
    def updateData(self, my_dict):
71 
        """通过影片名称去更新出字幕时间"""
72 
        self.db.set_character_set('utf8')
73 
        filmTitle = my_dict.get('film_title')
74 
        captionTime = my_dict.get('caption_time')
75 
        sql = "UPDATE versions_update_wechat SET caption_time='%s' WHERE film_title='%s'" % (captionTime, filmTitle)
76 
        #执行SQL语句
77 
        try:
78 
            result = self.cur.execute(sql)
79 
            self.db.commit()
80 
        except MySQLdb.Error, e:
81 
            # 发生错误时回滚
82 
            self.db.rollback()
83
84
85 
    """通过影片名称去数据库中查询"""
86 
    def findFilmByfilmTitle(self, filmTitile):
87 
        self.db.set_character_set('utf8')
88 
        sql = "select * from versions_update_wechat where film_title='%s'" % (filmTitile)
89 
        self.cur.execute(sql)
90 
        results = self.cur.fetchall()
91 
        self.db.commit()
92 
        return results
93

二進制
mysql.pyc
查看文件


+ 1728 - 0
nohup.out
查看文件 

@ -0,0 +1,1728 @@
1 
********************************************************************************
2 
film_type 剧情/
3 
dcp_size 64.54 GB
4 
color_space XYZ
5 
film_scope Flat 1.85
6 
film_title 大世界[Have a Nice Day]
7 
caption_time 别着急，还木有出来呢～～
8 
film_duration 01:18:28
9 
macro_format JPEG 2000
10 
dcp_name ""
11 
language_version 国语
12 
film_track 5.1
13 
********************************************************************************
14 
film_type 犯罪/喜剧/悬疑/
15 
dcp_size 131.18 GB
16 
color_space XYZ
17 
film_scope Scope 2.39
18 
film_title 迷镇凶案[Suburbicon]
19 
caption_time 别着急，还木有出来呢～～
20 
film_duration 01:44:08
21 
macro_format JPEG 2000
22 
dcp_name ""
23 
language_version 国语 / 原版
24 
film_track 5.1
25 
********************************************************************************
26 
film_type 动画/家庭/冒险/西部/
27 
dcp_size 72.29 GB
28 
color_space XYZ
29 
film_scope Scope 2.39
30 
film_title 妈妈咪鸭[Duck Duck Goose]
31 
caption_time 别着急，还木有出来呢～～
32 
film_duration 01:31:21
33 
macro_format JPEG 2000
34 
dcp_name ""
35 
language_version 国语
36 
film_track 5.1
37 
********************************************************************************
38 
film_type 动作/剧情/历史/
39 
dcp_size 144.61 GB
40 
color_space XYZ
41 
film_scope Scope 2.39
42 
film_title 太空救援[Salyut 7]
43 
caption_time 别着急，还木有出来呢～～
44 
film_duration 01:43:33
45 
macro_format JPEG 2000
46 
dcp_name ""
47 
language_version 国语 / 原版
48 
film_track 5.1
49 
********************************************************************************
50 
film_type 爱情/剧情/同性/
51 
dcp_size 85.13 GB
52 
color_space XYZ
53 
film_scope Scope 2.39
54 
film_title 无法触碰都爱[Doushitemo furetakunai]
55 
caption_time 别着急，还木有出来呢～～
56 
film_duration 01:40:14
57 
macro_format JPEG 2000
58 
dcp_name ""
59 
language_version 日语/译制
60 
film_track 5.1
61 
********************************************************************************
62 
film_type 剧情/
63 
dcp_size 108.14 GB
64 
color_space XYZ
65 
film_scope Scope 2.39
66 
film_title 咖啡风暴[Coffee]
67 
caption_time 01:48:48
68 
film_duration 01:53:33
69 
macro_format JPEG 2000
70 
dcp_name ""
71 
language_version 国语
72 
film_track 5.1
73 
********************************************************************************
74 
film_type 剧情/
75 
dcp_size 82.4 GB
76 
color_space XYZ
77 
film_scope Scope 2.39
78 
film_title 丢心[LOST CONSCIENCE]
79 
caption_time 别着急，还木有出来呢～～
80 
film_duration 01:43:15
81 
macro_format JPEG 2000
82 
dcp_name ""
83 
language_version 国语
84 
film_track 5.1
85 
********************************************************************************
86 
film_type 动画/儿童/奇幻/
87 
dcp_size 80.08 GB
88 
color_space XYZ
89 
film_scope Flat 1.85
90 
film_title 咕噜咕噜美人鱼2[Gulu Mermaid 2]
91 
caption_time 01:29:50
92 
film_duration 01:33:16
93 
macro_format JPEG 2000
94 
dcp_name ""
95 
language_version 国语
96 
film_track 5.1
97 
********************************************************************************
98 
film_type 奇幻/喜剧/
99 
dcp_size 153.85 GB
100 
color_space XYZ
101 
film_scope Scope 2.39
102 
film_title 二代妖精之今生有幸[Hanson and the Beast]
103 
caption_time 01:45:24
104 
film_duration 01:51:41
105 
macro_format JPEG 2000
106 
dcp_name ""
107 
language_version 国语
108 
film_track 5.1
109 
********************************************************************************
110 
film_type 家庭/喜剧/
111 
dcp_size 115.66 GB
112 
color_space XYZ
113 
film_scope Scope 2.39
114 
film_title 圣诞奇妙公司[Santa & Cie]
115 
caption_time 01:33:15
116 
film_duration 01:39:04
117 
macro_format JPEG 2000
118 
dcp_name ""
119 
language_version 国语 / 原版
120 
film_track 5.1
121 
********************************************************************************
122 
film_type 动作/犯罪/剧情/
123 
dcp_size 151.69 GB
124 
color_space XYZ
125 
film_scope Scope 2.39
126 
film_title 心理罪之城市之光[The Liquidator]
127 
caption_time 01:57:08
128 
film_duration 02:05:25
129 
macro_format JPEG 2000
130 
dcp_name ""
131 
language_version 国语
132 
film_track 5.1
133 
********************************************************************************
134 
film_type 奇幻/武侠/
135 
dcp_size 170.26 GB
136 
color_space XYZ
137 
film_scope Scope 2.39
138 
film_title 妖猫传[Legend of the Demon Cat]
139 
caption_time 02:07:40
140 
film_duration 02:11:01
141 
macro_format JPEG 2000
142 
dcp_name ""
143 
language_version 国语
144 
film_track 5.1
145 
********************************************************************************
146 
film_type 动作/科幻/冒险/
147 
dcp_size 186.42 GB
148 
color_space XYZ
149 
film_scope Scope 2.39
150 
film_title 星球大战8：最后的绝地武士[Star Wars: The Last Jedi]
151 
caption_time 别着急，还木有出来呢～～
152 
film_duration 02:31:45
153 
macro_format JPEG 2000
154 
dcp_name ""
155 
language_version 国语 / 英语
156 
film_track 5.1
157 
********************************************************************************
158 
film_type 剧情/
159 
dcp_size 111 GB
160 
color_space XYZ
161 
film_scope Scope 2.39
162 
film_title 天籁梦想[TheSoundofaDream]
163 
caption_time 别着急，还木有出来呢～～
164 
film_duration 01:26:10
165 
macro_format JPEG 2000
166 
dcp_name ""
167 
language_version 普通话
168 
film_track 5.1
169 
********************************************************************************
170 
film_type 剧情/奇幻/
171 
dcp_size 146.12 GB
172 
color_space XYZ
173 
film_scope Scope 2.39
174 
film_title 解忧杂货店[NAMIYA]
175 
caption_time 01:45:44
176 
film_duration 01:49:59
177 
macro_format JPEG 2000
178 
dcp_name ""
179 
language_version 国语 / 粤语
180 
film_track 5.1
181 
********************************************************************************
182 
film_type 喜剧/
183 
dcp_size 119.31 GB
184 
color_space XYZ
185 
film_scope Scope 2.39
186 
film_title 妖铃铃[Gold Buster]
187 
caption_time 01:24:33
188 
film_duration 01:29:37
189 
macro_format JPEG 2000
190 
dcp_name ""
191 
language_version 国语 / 粤语
192 
film_track 5.1
193 
********************************************************************************
194 
film_type 爱情/
195 
dcp_size 37.05 GB
196 
color_space sRGB
197 
film_scope Flat 1.77
198 
film_title 我来过[I WAS HERE]
199 
caption_time 别着急，还木有出来呢～～
200 
film_duration 01:33:07
201 
macro_format MPEG-2
202 
dcp_name ""
203 
language_version 国语
204 
film_track 5.1
205 
********************************************************************************
206 
film_type 剧情/
207 
dcp_size 86.54 GB
208 
color_space XYZ
209 
film_scope Scope 2.39
210 
film_title 十七后与青春化敌为友[Dance with Youth]
211 
caption_time 别着急，还木有出来呢～～
212 
film_duration 01:30:45
213 
macro_format JPEG 2000
214 
dcp_name ""
215 
language_version 国语
216 
film_track 5.1
217 
********************************************************************************
218 
film_type 动画/家庭/冒险/奇幻/
219 
dcp_size 63.36 GB
220 
color_space XYZ
221 
film_scope Scope 2.35
222 
film_title 小猫巴克里[Barkley]
223 
caption_time 01:22:43
224 
film_duration 01:26:00
225 
macro_format JPEG 2000
226 
dcp_name ""
227 
language_version 国语
228 
film_track 5.1
229 
********************************************************************************
230 
film_type 故事/
231 
dcp_size 94.08 GB
232 
color_space XYZ
233 
film_scope Scope 2.39
234 
film_title 远亲[DISTANT RELATIVE]
235 
caption_time 别着急，还木有出来呢～～
236 
film_duration 01:32:11
237 
macro_format JPEG 2000
238 
dcp_name ""
239 
language_version 国语
240 
film_track 5.1
241 
********************************************************************************
242 
film_type 爱情/喜剧/
243 
dcp_size 148.48 GB
244 
color_space XYZ
245 
film_scope Scope 2.39
246 
film_title 前任3：再见前任[The Ex-File:The Return OF The Exes]
247 
caption_time 01:55:34
248 
film_duration 02:00:31
249 
macro_format JPEG 2000
250 
dcp_name ""
251 
language_version 国语
252 
film_track 5.1
253 
********************************************************************************
254 
film_type
255 
dcp_size 182.97 GB
256 
color_space XYZ
257 
film_scope Scope 2.39
258 
film_title 机器之血[Bleeding Steel]
259 
caption_time 01:43:54
260 
film_duration 01:50:24
261 
macro_format JPEG 2000
262 
dcp_name ""
263 
language_version 国语
264 
film_track 5.1
265 
********************************************************************************
266 
film_type 剧情/
267 
dcp_size 100.32 GB
268 
color_space XYZ
269 
film_scope Scope 2.39
270 
film_title “醉”佳导演[Come On， Teacher]
271 
caption_time 别着急，还木有出来呢～～
272 
film_duration 01:28:48
273 
macro_format JPEG 2000
274 
dcp_name ""
275 
language_version 国语
276 
film_track 5.1
277 
********************************************************************************
278 
film_type 青春/校园/
279 
dcp_size 72.64 GB
280 
color_space XYZ
281 
film_scope Scope 2.39
282 
film_title 热血时代[Young Blood]
283 
caption_time 01:34:05
284 
film_duration 01:37:50
285 
macro_format JPEG 2000
286 
dcp_name ""
287 
language_version 国语
288 
film_track 5.1
289 
********************************************************************************
290 
film_type 故事/
291 
dcp_size 118.19 GB
292 
color_space XYZ
293 
film_scope Scope 2.39
294 
film_title 爱的帕斯卡[LOVE PASCAL]
295 
caption_time 别着急，还木有出来呢～～
296 
film_duration 01:38:26
297 
macro_format JPEG 2000
298 
dcp_name ""
299 
language_version 国语
300 
film_track 5.1
301 
********************************************************************************
302 
film_type 犯罪/惊悚/
303 
dcp_size 99.87 GB
304 
color_space XYZ
305 
film_scope Flat 1.85
306 
film_title 逃离现场[ESCAPING]
307 
caption_time 01:22:46
308 
film_duration 01:25:31
309 
macro_format JPEG 2000
310 
dcp_name ""
311 
language_version 国语
312 
film_track 5.1
313 
********************************************************************************
314 
film_type 历史/西部/
315 
dcp_size 126.09 GB
316 
color_space XYZ
317 
film_scope Scope 2.39
318 
film_title 金珠玛米[The Chainbreakers]
319 
caption_time 01:32:27
320 
film_duration 01:37:30
321 
macro_format JPEG 2000
322 
dcp_name ""
323 
language_version 国语
324 
film_track 5.1
325 
********************************************************************************
326 
film_type 剧情/
327 
dcp_size 128.15 GB
328 
color_space XYZ
329 
film_scope Flat 1.85
330 
film_title 老兽[Old Beast]
331 
caption_time 01:47:33
332 
film_duration 01:50:55
333 
macro_format JPEG 2000
334 
dcp_name ""
335 
language_version 国语
336 
film_track 5.1
337 
********************************************************************************
338 
film_type 惊悚/恐怖/
339 
dcp_size 57.53 GB
340 
color_space XYZ
341 
film_scope Scope 2.39
342 
film_title 惊魂七夜[SENEN FRIGHT NIGHTS]
343 
caption_time 01:30:02
344 
film_duration 01:31:33
345 
macro_format JPEG 2000
346 
dcp_name ""
347 
language_version 国语
348 
film_track 5.1
349 
********************************************************************************
350 
film_type 惊悚/恐怖/
351 
dcp_size 84.27 GB
352 
color_space XYZ
353 
film_scope Scope 2.39
354 
film_title 墨玉太极[JADE OF TAI CHI]
355 
caption_time 01:31:06
356 
film_duration 01:33:23
357 
macro_format JPEG 2000
358 
dcp_name ""
359 
language_version 国语
360 
film_track 5.1
361 
********************************************************************************
362 
film_type 爱情/剧情/
363 
dcp_size 46.21 GB
364 
color_space sRGB
365 
film_scope Flat 1.77
366 
film_title 悔恨[Lose Love Forever]
367 
caption_time 01:53:22
368 
film_duration 01:56:09
369 
macro_format MPEG-2
370 
dcp_name ""
371 
language_version 国语
372 
film_track 5.1
373 
********************************************************************************
374 
film_type 动作/奇幻/武侠/
375 
dcp_size 188.41 GB
376 
color_space XYZ
377 
film_scope Flat 1.85
378 
film_title 奇门遁甲[The Thousand Faces of Dun jia]
379 
caption_time 01:44:45
380 
film_duration 01:52:39
381 
macro_format JPEG 2000
382 
dcp_name ""
383 
language_version 国语
384 
film_track 5.1
385 
********************************************************************************
386 
film_type 爱情/剧情/喜剧/
387 
dcp_size 118.09 GB
388 
color_space XYZ
389 
film_scope Flat 1.85
390 
film_title 假如王子睡着了[The Dreaming Man]
391 
caption_time 01:36:16
392 
film_duration 01:41:23
393 
macro_format JPEG 2000
394 
dcp_name ""
395 
language_version 国语
396 
film_track 5.1
397 
********************************************************************************
398 
film_type 剧情/
399 
dcp_size 146.67 GB
400 
color_space XYZ
401 
film_scope Scope 2.39
402 
film_title 帕丁顿熊2[Paddington 2]
403 
caption_time 01:36:56
404 
film_duration 01:43:30
405 
macro_format JPEG 2000
406 
dcp_name ""
407 
language_version 国语 / 原版
408 
film_track 5.1
409 
********************************************************************************
410 
film_type 动作/犯罪/惊悚/
411 
dcp_size 95.41 GB
412 
color_space XYZ
413 
film_scope Scope 2.39
414 
film_title 双面劫匪[Heist]
415 
caption_time 01:26:31
416 
film_duration 01:31:53
417 
macro_format JPEG 2000
418 
dcp_name ""
419 
language_version 国语 / 原版
420 
film_track 5.1
421 
********************************************************************************
422 
film_type 惊悚/剧情/冒险/
423 
dcp_size 85.2 GB
424 
color_space XYZ
425 
film_scope Scope 2.39
426 
film_title 鲨海[47 Meters Down]
427 
caption_time 01:23:57
428 
film_duration 01:28:59
429 
macro_format JPEG 2000
430 
dcp_name ""
431 
language_version 国语 / 原版
432 
film_track 5.1
433 
********************************************************************************
434 
film_type 警匪/
435 
dcp_size 165.72 GB
436 
color_space XYZ
437 
film_scope Scope 2.39
438 
film_title 巨额来电[The Big Call]
439 
caption_time 01:59:10
440 
film_duration 02:04:43
441 
macro_format JPEG 2000
442 
dcp_name ""
443 
language_version 国语
444 
film_track 5.1
445 
********************************************************************************
446 
film_type 传记/动画/犯罪/剧情/
447 
dcp_size 117.08 GB
448 
color_space XYZ
449 
film_scope Flat 1.85
450 
film_title 至爱梵高·星空之谜[Loving Vincent]
451 
caption_time 01:31:11
452 
film_duration 01:34:15
453 
macro_format JPEG 2000
454 
dcp_name ""
455 
language_version 国语 / 原版
456 
film_track 5.1
457 
********************************************************************************
458 
film_type 传记/剧情/灾难/
459 
dcp_size 136.99 GB
460 
color_space XYZ
461 
film_scope Scope 2.39
462 
film_title 勇往直前[Only the Brave]
463 
caption_time 01:58:57
464 
film_duration 02:06:35
465 
macro_format JPEG 2000
466 
dcp_name ""
467 
language_version 国语 / 原版
468 
film_track 5.1
469 
********************************************************************************
470 
film_type 动作/喜剧/
471 
dcp_size 99.45 GB
472 
color_space XYZ
473 
film_scope Scope 2.39
474 
film_title 疯狂特警队[Raid Dingue]
475 
caption_time 01:42:27
476 
film_duration 01:46:31
477 
macro_format JPEG 2000
478 
dcp_name ""
479 
language_version 国语 / 原版
480 
film_track 5.1
481 
********************************************************************************
482 
film_type 剧情/喜剧/
483 
dcp_size 124.43 GB
484 
color_space XYZ
485 
film_scope Scope 2.39
486 
film_title 相声大电影之我要幸福
487 
caption_time 01:28:44
488 
film_duration 01:32:02
489 
macro_format JPEG 2000
490 
dcp_name ""
491 
language_version 国语
492 
film_track 5.1
493 
********************************************************************************
494 
film_type 犯罪/喜剧/
495 
dcp_size 120.52 GB
496 
color_space XYZ
497 
film_scope Scope 2.39
498 
film_title 夺金四贱客[Four Against the Bank]
499 
caption_time 01:28:55
500 
film_duration 01:35:35
501 
macro_format JPEG 2000
502 
dcp_name ""
503 
language_version 国语 / 原版
504 
film_track 5.1
505 
********************************************************************************
506 
film_type 动作/战争/
507 
dcp_size 169.41 GB
508 
color_space XYZ
509 
film_scope Scope 2.39
510 
film_title 维京：王者之战[Viking]
511 
caption_time 01:59:30
512 
film_duration 02:08:06
513 
macro_format JPEG 2000
514 
dcp_name ""
515 
language_version 国语 / 原版
516 
film_track 5.1
517 
********************************************************************************
518 
film_type 爱情/剧情/
519 
dcp_size 37.05 GB
520 
color_space 709
521 
film_scope Flat 1.77
522 
film_title 我来过
523 
caption_time 别着急，还木有出来呢～～
524 
film_duration 01:33:07
525 
macro_format MPEG-2
526 
dcp_name ""
527 
language_version 普通话
528 
film_track 5.1
529 
********************************************************************************
530 
film_type 剧情/犯罪/冒险
531 
dcp_size 111.07 GB
532 
color_space XYZ
533 
film_scope Scope 2.39
534 
film_title 大秦直道[THE GREAT QINZHIDAO]
535 
caption_time 01:27:08
536 
film_duration 01:29:35
537 
macro_format JPEG 2000
538 
dcp_name ""
539 
language_version 普通话
540 
film_track 5.1
541 
[2018-01-04 11:15:54] 连接数据库错误，原因2002: Can't connect to local MySQL server through socket '/tmp/mysql.sock' (2)
542 
********************************************************************************
543 
Traceback (most recent call last):
544 
  File "/webroot/spider/rov8.py", line 222, in <module>
545 
    rov.main()
546 
  File "/webroot/spider/rov8.py", line 216, in main
547 
    self.getContents(1)
548 
  File "/webroot/spider/rov8.py", line 65, in getContents
549 
    self.getDetailPage('http://www.rov8.com/' + url)
550 
  File "/webroot/spider/rov8.py", line 75, in getDetailPage
551 
    self.getFiled(div, film_title)
552 
  File "/webroot/spider/rov8.py", line 149, in getFiled
553 
    self.list2dict(rlists)
554 
  File "/webroot/spider/rov8.py", line 199, in list2dict
555 
    self.mysql.dealData(result_dict)
556 
  File "/opt/webroot/spider/mysql.py", line 56, in dealData
557 
    self.db.set_character_set('utf8')
558 
AttributeError: Mysql instance has no attribute 'db'
559 
********************************************************************************
560 
film_type 剧情/
561 
dcp_size 64.54 GB
562 
color_space XYZ
563 
film_scope Flat 1.85
564 
film_title 大世界[Have a Nice Day]
565 
caption_time 别着急，还木有出来呢～～
566 
film_duration 01:18:28
567 
macro_format JPEG 2000
568 
dcp_name ""
569 
language_version 国语
570 
film_track 5.1
571 
long_biao 暂无
572 
********************************************************************************
573 
film_type 犯罪/喜剧/悬疑/
574 
dcp_size 131.18 GB
575 
color_space XYZ
576 
film_scope Scope 2.39
577 
film_title 迷镇凶案[Suburbicon]
578 
caption_time 别着急，还木有出来呢～～
579 
film_duration 01:44:08
580 
macro_format JPEG 2000
581 
dcp_name ""
582 
language_version 国语 / 原版
583 
film_track 5.1
584 
long_biao 暂无
585 
********************************************************************************
586 
film_type 动画/家庭/冒险/西部/
587 
dcp_size 72.29 GB
588 
color_space XYZ
589 
film_scope Scope 2.39
590 
film_title 妈妈咪鸭[Duck Duck Goose]
591 
caption_time 别着急，还木有出来呢～～
592 
film_duration 01:31:21
593 
macro_format JPEG 2000
594 
dcp_name ""
595 
language_version 国语
596 
film_track 5.1
597 
long_biao 暂无
598 
********************************************************************************
599 
film_type 动作/剧情/历史/
600 
dcp_size 144.61 GB
601 
color_space XYZ
602 
film_scope Scope 2.39
603 
film_title 太空救援[Salyut 7]
604 
caption_time 别着急，还木有出来呢～～
605 
film_duration 01:43:33
606 
macro_format JPEG 2000
607 
dcp_name ""
608 
language_version 国语 / 原版
609 
film_track 5.1
610 
long_biao 暂无
611 
********************************************************************************
612 
film_type 爱情/剧情/同性/
613 
dcp_size 85.13 GB
614 
color_space XYZ
615 
film_scope Scope 2.39
616 
film_title 无法触碰都爱[Doushitemo furetakunai]
617 
caption_time 别着急，还木有出来呢～～
618 
film_duration 01:40:14
619 
macro_format JPEG 2000
620 
dcp_name ""
621 
language_version 日语/译制
622 
film_track 5.1
623 
long_biao 暂无
624 
********************************************************************************
625 
film_type 剧情/
626 
dcp_size 108.14 GB
627 
color_space XYZ
628 
film_scope Scope 2.39
629 
film_title 咖啡风暴[Coffee]
630 
caption_time 01:48:48
631 
film_duration 01:53:33
632 
macro_format JPEG 2000
633 
dcp_name ""
634 
language_version 国语
635 
film_track 5.1
636 
long_biao 暂无
637 
********************************************************************************
638 
film_type 剧情/
639 
dcp_size 82.4 GB
640 
color_space XYZ
641 
film_scope Scope 2.39
642 
film_title 丢心[LOST CONSCIENCE]
643 
caption_time 别着急，还木有出来呢～～
644 
film_duration 01:43:15
645 
macro_format JPEG 2000
646 
dcp_name ""
647 
language_version 国语
648 
film_track 5.1
649 
long_biao 暂无
650 
********************************************************************************
651 
film_type 动画/儿童/奇幻/
652 
dcp_size 80.08 GB
653 
color_space XYZ
654 
film_scope Flat 1.85
655 
film_title 咕噜咕噜美人鱼2[Gulu Mermaid 2]
656 
caption_time 01:29:50
657 
film_duration 01:33:16
658 
macro_format JPEG 2000
659 
dcp_name ""
660 
language_version 国语
661 
film_track 5.1
662 
long_biao 暂无
663 
********************************************************************************
664 
film_type 奇幻/喜剧/
665 
dcp_size 153.85 GB
666 
color_space XYZ
667 
film_scope Scope 2.39
668 
film_title 二代妖精之今生有幸[Hanson and the Beast]
669 
caption_time 01:45:24
670 
film_duration 01:51:41
671 
macro_format JPEG 2000
672 
dcp_name ""
673 
language_version 国语
674 
film_track 5.1
675 
long_biao 暂无
676 
********************************************************************************
677 
film_type 家庭/喜剧/
678 
dcp_size 115.66 GB
679 
color_space XYZ
680 
film_scope Scope 2.39
681 
film_title 圣诞奇妙公司[Santa & Cie]
682 
caption_time 01:33:15
683 
film_duration 01:39:04
684 
macro_format JPEG 2000
685 
dcp_name ""
686 
language_version 国语 / 原版
687 
film_track 5.1
688 
long_biao 暂无
689 
********************************************************************************
690 
film_type 动作/犯罪/剧情/
691 
dcp_size 151.69 GB
692 
color_space XYZ
693 
film_scope Scope 2.39
694 
film_title 心理罪之城市之光[The Liquidator]
695 
caption_time 01:57:08
696 
film_duration 02:05:25
697 
macro_format JPEG 2000
698 
dcp_name ""
699 
language_version 国语
700 
film_track 5.1
701 
long_biao 暂无
702 
********************************************************************************
703 
film_type 奇幻/武侠/
704 
dcp_size 170.26 GB
705 
color_space XYZ
706 
film_scope Scope 2.39
707 
film_title 妖猫传[Legend of the Demon Cat]
708 
caption_time 02:07:40
709 
film_duration 02:11:01
710 
macro_format JPEG 2000
711 
dcp_name ""
712 
language_version 国语
713 
film_track 5.1
714 
long_biao 暂无
715 
********************************************************************************
716 
film_type 动作/科幻/冒险/
717 
dcp_size 186.42 GB
718 
color_space XYZ
719 
film_scope Scope 2.39
720 
film_title 星球大战8：最后的绝地武士[Star Wars: The Last Jedi]
721 
caption_time 别着急，还木有出来呢～～
722 
film_duration 02:31:45
723 
macro_format JPEG 2000
724 
dcp_name ""
725 
language_version 国语 / 英语
726 
film_track 5.1
727 
long_biao 暂无
728 
********************************************************************************
729 
film_type 剧情/
730 
dcp_size 111 GB
731 
color_space XYZ
732 
film_scope Scope 2.39
733 
film_title 天籁梦想[TheSoundofaDream]
734 
caption_time 别着急，还木有出来呢～～
735 
film_duration 01:26:10
736 
macro_format JPEG 2000
737 
dcp_name ""
738 
language_version 普通话
739 
film_track 5.1
740 
long_biao 暂无
741 
********************************************************************************
742 
film_type 剧情/奇幻/
743 
dcp_size 146.12 GB
744 
color_space XYZ
745 
film_scope Scope 2.39
746 
film_title 解忧杂货店[NAMIYA]
747 
caption_time 01:45:44
748 
film_duration 01:49:59
749 
macro_format JPEG 2000
750 
dcp_name ""
751 
language_version 国语 / 粤语
752 
film_track 5.1
753 
long_biao 暂无
754 
********************************************************************************
755 
film_type 喜剧/
756 
dcp_size 119.31 GB
757 
color_space XYZ
758 
film_scope Scope 2.39
759 
film_title 妖铃铃[Gold Buster]
760 
caption_time 01:24:33
761 
film_duration 01:29:37
762 
macro_format JPEG 2000
763 
dcp_name ""
764 
language_version 国语 / 粤语
765 
film_track 5.1
766 
long_biao 暂无
767 
********************************************************************************
768 
film_type 爱情/
769 
dcp_size 37.05 GB
770 
color_space sRGB
771 
film_scope Flat 1.77
772 
film_title 我来过[I WAS HERE]
773 
caption_time 别着急，还木有出来呢～～
774 
film_duration 01:33:07
775 
macro_format MPEG-2
776 
dcp_name ""
777 
language_version 国语
778 
film_track 5.1
779 
long_biao 暂无
780 
********************************************************************************
781 
film_type 剧情/
782 
dcp_size 86.54 GB
783 
color_space XYZ
784 
film_scope Scope 2.39
785 
film_title 十七后与青春化敌为友[Dance with Youth]
786 
caption_time 别着急，还木有出来呢～～
787 
film_duration 01:30:45
788 
macro_format JPEG 2000
789 
dcp_name ""
790 
language_version 国语
791 
film_track 5.1
792 
long_biao 暂无
793 
********************************************************************************
794 
film_type 动画/家庭/冒险/奇幻/
795 
dcp_size 63.36 GB
796 
color_space XYZ
797 
film_scope Scope 2.35
798 
film_title 小猫巴克里[Barkley]
799 
caption_time 01:22:43
800 
film_duration 01:26:00
801 
macro_format JPEG 2000
802 
dcp_name ""
803 
language_version 国语
804 
film_track 5.1
805 
long_biao 暂无
806 
********************************************************************************
807 
film_type 故事/
808 
dcp_size 94.08 GB
809 
color_space XYZ
810 
film_scope Scope 2.39
811 
film_title 远亲[DISTANT RELATIVE]
812 
caption_time 别着急，还木有出来呢～～
813 
film_duration 01:32:11
814 
macro_format JPEG 2000
815 
dcp_name ""
816 
language_version 国语
817 
film_track 5.1
818 
long_biao 暂无
819 
********************************************************************************
820 
film_type 爱情/喜剧/
821 
dcp_size 148.48 GB
822 
color_space XYZ
823 
film_scope Scope 2.39
824 
film_title 前任3：再见前任[The Ex-File:The Return OF The Exes]
825 
caption_time 01:55:34
826 
film_duration 02:00:31
827 
macro_format JPEG 2000
828 
dcp_name ""
829 
language_version 国语
830 
film_track 5.1
831 
long_biao 暂无
832 
********************************************************************************
833 
film_type
834 
dcp_size 182.97 GB
835 
color_space XYZ
836 
film_scope Scope 2.39
837 
film_title 机器之血[Bleeding Steel]
838 
caption_time 01:43:54
839 
film_duration 01:50:24
840 
macro_format JPEG 2000
841 
dcp_name ""
842 
language_version 国语
843 
film_track 5.1
844 
long_biao 暂无
845 
********************************************************************************
846 
film_type 剧情/
847 
dcp_size 100.32 GB
848 
color_space XYZ
849 
film_scope Scope 2.39
850 
film_title “醉”佳导演[Come On， Teacher]
851 
caption_time 别着急，还木有出来呢～～
852 
film_duration 01:28:48
853 
macro_format JPEG 2000
854 
dcp_name ""
855 
language_version 国语
856 
film_track 5.1
857 
long_biao 暂无
858 
********************************************************************************
859 
film_type 青春/校园/
860 
dcp_size 72.64 GB
861 
color_space XYZ
862 
film_scope Scope 2.39
863 
film_title 热血时代[Young Blood]
864 
caption_time 01:34:05
865 
film_duration 01:37:50
866 
macro_format JPEG 2000
867 
dcp_name ""
868 
language_version 国语
869 
film_track 5.1
870 
long_biao 暂无
871 
********************************************************************************
872 
film_type 故事/
873 
dcp_size 118.19 GB
874 
color_space XYZ
875 
film_scope Scope 2.39
876 
film_title 爱的帕斯卡[LOVE PASCAL]
877 
caption_time 别着急，还木有出来呢～～
878 
film_duration 01:38:26
879 
macro_format JPEG 2000
880 
dcp_name ""
881 
language_version 国语
882 
film_track 5.1
883 
long_biao 暂无
884 
********************************************************************************
885 
film_type 犯罪/惊悚/
886 
dcp_size 99.87 GB
887 
color_space XYZ
888 
film_scope Flat 1.85
889 
film_title 逃离现场[ESCAPING]
890 
caption_time 01:22:46
891 
film_duration 01:25:31
892 
macro_format JPEG 2000
893 
dcp_name ""
894 
language_version 国语
895 
film_track 5.1
896 
long_biao 暂无
897 
********************************************************************************
898 
film_type 历史/西部/
899 
dcp_size 126.09 GB
900 
color_space XYZ
901 
film_scope Scope 2.39
902 
film_title 金珠玛米[The Chainbreakers]
903 
caption_time 01:32:27
904 
film_duration 01:37:30
905 
macro_format JPEG 2000
906 
dcp_name ""
907 
language_version 国语
908 
film_track 5.1
909 
long_biao 暂无
910 
********************************************************************************
911 
film_type 剧情/
912 
dcp_size 128.15 GB
913 
color_space XYZ
914 
film_scope Flat 1.85
915 
film_title 老兽[Old Beast]
916 
caption_time 01:47:33
917 
film_duration 01:50:55
918 
macro_format JPEG 2000
919 
dcp_name ""
920 
language_version 国语
921 
film_track 5.1
922 
long_biao 暂无
923 
********************************************************************************
924 
film_type 惊悚/恐怖/
925 
dcp_size 57.53 GB
926 
color_space XYZ
927 
film_scope Scope 2.39
928 
film_title 惊魂七夜[SENEN FRIGHT NIGHTS]
929 
caption_time 01:30:02
930 
film_duration 01:31:33
931 
macro_format JPEG 2000
932 
dcp_name ""
933 
language_version 国语
934 
film_track 5.1
935 
long_biao 暂无
936 
********************************************************************************
937 
film_type 惊悚/恐怖/
938 
dcp_size 84.27 GB
939 
color_space XYZ
940 
film_scope Scope 2.39
941 
film_title 墨玉太极[JADE OF TAI CHI]
942 
caption_time 01:31:06
943 
film_duration 01:33:23
944 
macro_format JPEG 2000
945 
dcp_name ""
946 
language_version 国语
947 
film_track 5.1
948 
long_biao 暂无
949 
********************************************************************************
950 
film_type 爱情/剧情/
951 
dcp_size 46.21 GB
952 
color_space sRGB
953 
film_scope Flat 1.77
954 
film_title 悔恨[Lose Love Forever]
955 
caption_time 01:53:22
956 
film_duration 01:56:09
957 
macro_format MPEG-2
958 
dcp_name ""
959 
language_version 国语
960 
film_track 5.1
961 
long_biao 暂无
962 
********************************************************************************
963 
film_type 动作/奇幻/武侠/
964 
dcp_size 188.41 GB
965 
color_space XYZ
966 
film_scope Flat 1.85
967 
film_title 奇门遁甲[The Thousand Faces of Dun jia]
968 
caption_time 01:44:45
969 
film_duration 01:52:39
970 
macro_format JPEG 2000
971 
dcp_name ""
972 
language_version 国语
973 
film_track 5.1
974 
long_biao 暂无
975 
********************************************************************************
976 
film_type 爱情/剧情/喜剧/
977 
dcp_size 118.09 GB
978 
color_space XYZ
979 
film_scope Flat 1.85
980 
film_title 假如王子睡着了[The Dreaming Man]
981 
caption_time 01:36:16
982 
film_duration 01:41:23
983 
macro_format JPEG 2000
984 
dcp_name ""
985 
language_version 国语
986 
film_track 5.1
987 
long_biao 暂无
988 
********************************************************************************
989 
film_type 剧情/
990 
dcp_size 146.67 GB
991 
color_space XYZ
992 
film_scope Scope 2.39
993 
film_title 帕丁顿熊2[Paddington 2]
994 
caption_time 01:36:56
995 
film_duration 01:43:30
996 
macro_format JPEG 2000
997 
dcp_name ""
998 
language_version 国语 / 原版
999 
film_track 5.1
1000 
long_biao 暂无
1001 
********************************************************************************
1002 
film_type 动作/犯罪/惊悚/
1003 
dcp_size 95.41 GB
1004 
color_space XYZ
1005 
film_scope Scope 2.39
1006 
film_title 双面劫匪[Heist]
1007 
caption_time 01:26:31
1008 
film_duration 01:31:53
1009 
macro_format JPEG 2000
1010 
dcp_name ""
1011 
language_version 国语 / 原版
1012 
film_track 5.1
1013 
long_biao 暂无
1014 
********************************************************************************
1015 
film_type 惊悚/剧情/冒险/
1016 
dcp_size 85.2 GB
1017 
color_space XYZ
1018 
film_scope Scope 2.39
1019 
film_title 鲨海[47 Meters Down]
1020 
caption_time 01:23:57
1021 
film_duration 01:28:59
1022 
macro_format JPEG 2000
1023 
dcp_name ""
1024 
language_version 国语 / 原版
1025 
film_track 5.1
1026 
long_biao 暂无
1027 
********************************************************************************
1028 
film_type 警匪/
1029 
dcp_size 165.72 GB
1030 
color_space XYZ
1031 
film_scope Scope 2.39
1032 
film_title 巨额来电[The Big Call]
1033 
caption_time 01:59:10
1034 
film_duration 02:04:43
1035 
macro_format JPEG 2000
1036 
dcp_name ""
1037 
language_version 国语
1038 
film_track 5.1
1039 
long_biao 暂无
1040 
********************************************************************************
1041 
film_type 传记/动画/犯罪/剧情/
1042 
dcp_size 117.08 GB
1043 
color_space XYZ
1044 
film_scope Flat 1.85
1045 
film_title 至爱梵高·星空之谜[Loving Vincent]
1046 
caption_time 01:31:11
1047 
film_duration 01:34:15
1048 
macro_format JPEG 2000
1049 
dcp_name ""
1050 
language_version 国语 / 原版
1051 
film_track 5.1
1052 
long_biao 暂无
1053 
********************************************************************************
1054 
film_type 传记/剧情/灾难/
1055 
dcp_size 136.99 GB
1056 
color_space XYZ
1057 
film_scope Scope 2.39
1058 
film_title 勇往直前[Only the Brave]
1059 
caption_time 01:58:57
1060 
film_duration 02:06:35
1061 
macro_format JPEG 2000
1062 
dcp_name ""
1063 
language_version 国语 / 原版
1064 
film_track 5.1
1065 
long_biao 暂无
1066 
********************************************************************************
1067 
film_type 动作/喜剧/
1068 
dcp_size 99.45 GB
1069 
color_space XYZ
1070 
film_scope Scope 2.39
1071 
film_title 疯狂特警队[Raid Dingue]
1072 
caption_time 01:42:27
1073 
film_duration 01:46:31
1074 
macro_format JPEG 2000
1075 
dcp_name ""
1076 
language_version 国语 / 原版
1077 
film_track 5.1
1078 
long_biao 暂无
1079 
********************************************************************************
1080 
film_type 剧情/喜剧/
1081 
dcp_size 124.43 GB
1082 
color_space XYZ
1083 
film_scope Scope 2.39
1084 
film_title 相声大电影之我要幸福
1085 
caption_time 01:28:44
1086 
film_duration 01:32:02
1087 
macro_format JPEG 2000
1088 
dcp_name ""
1089 
language_version 国语
1090 
film_track 5.1
1091 
long_biao 暂无
1092 
********************************************************************************
1093 
film_type 犯罪/喜剧/
1094 
dcp_size 120.52 GB
1095 
color_space XYZ
1096 
film_scope Scope 2.39
1097 
film_title 夺金四贱客[Four Against the Bank]
1098 
caption_time 01:28:55
1099 
film_duration 01:35:35
1100 
macro_format JPEG 2000
1101 
dcp_name ""
1102 
language_version 国语 / 原版
1103 
film_track 5.1
1104 
long_biao 暂无
1105 
********************************************************************************
1106 
film_type 动作/战争/
1107 
dcp_size 169.41 GB
1108 
color_space XYZ
1109 
film_scope Scope 2.39
1110 
film_title 维京：王者之战[Viking]
1111 
caption_time 01:59:30
1112 
film_duration 02:08:06
1113 
macro_format JPEG 2000
1114 
dcp_name ""
1115 
language_version 国语 / 原版
1116 
film_track 5.1
1117 
long_biao 暂无
1118 
********************************************************************************
1119 
film_type 爱情/剧情/
1120 
dcp_size 37.05 GB
1121 
color_space 709
1122 
film_scope Flat 1.77
1123 
film_title 我来过
1124 
caption_time 别着急，还木有出来呢～～
1125 
film_duration 01:33:07
1126 
macro_format MPEG-2
1127 
dcp_name ""
1128 
language_version 普通话
1129 
film_track 5.1
1130 
long_biao 暂无
1131 
********************************************************************************
1132 
film_type 剧情/犯罪/冒险
1133 
dcp_size 111.07 GB
1134 
color_space XYZ
1135 
film_scope Scope 2.39
1136 
film_title 大秦直道[THE GREAT QINZHIDAO]
1137 
caption_time 01:27:08
1138 
film_duration 01:29:35
1139 
macro_format JPEG 2000
1140 
dcp_name ""
1141 
language_version 普通话
1142 
film_track 5.1
1143 
long_biao 暂无
1144 
********************************************************************************
1145 
film_type 剧情/
1146 
dcp_size 64.54 GB
1147 
color_space XYZ
1148 
film_scope Flat 1.85
1149 
film_title 大世界[Have a Nice Day]
1150 
caption_time 别着急，还木有出来呢～～
1151 
film_duration 01:18:28
1152 
macro_format JPEG 2000
1153 
dcp_name ""
1154 
language_version 国语
1155 
film_track 5.1
1156 
long_biao 暂无
1157 
********************************************************************************
1158 
film_type 犯罪/喜剧/悬疑/
1159 
dcp_size 131.18 GB
1160 
color_space XYZ
1161 
film_scope Scope 2.39
1162 
film_title 迷镇凶案[Suburbicon]
1163 
caption_time 别着急，还木有出来呢～～
1164 
film_duration 01:44:08
1165 
macro_format JPEG 2000
1166 
dcp_name ""
1167 
language_version 国语 / 原版
1168 
film_track 5.1
1169 
long_biao 暂无
1170 
********************************************************************************
1171 
film_type 动画/家庭/冒险/西部/
1172 
dcp_size 72.29 GB
1173 
color_space XYZ
1174 
film_scope Scope 2.39
1175 
film_title 妈妈咪鸭[Duck Duck Goose]
1176 
caption_time 别着急，还木有出来呢～～
1177 
film_duration 01:31:21
1178 
macro_format JPEG 2000
1179 
dcp_name ""
1180 
language_version 国语
1181 
film_track 5.1
1182 
long_biao 暂无
1183 
********************************************************************************
1184 
film_type 动作/剧情/历史/
1185 
dcp_size 144.61 GB
1186 
color_space XYZ
1187 
film_scope Scope 2.39
1188 
film_title 太空救援[Salyut 7]
1189 
caption_time 别着急，还木有出来呢～～
1190 
film_duration 01:43:33
1191 
macro_format JPEG 2000
1192 
dcp_name ""
1193 
language_version 国语 / 原版
1194 
film_track 5.1
1195 
long_biao 暂无
1196 
********************************************************************************
1197 
film_type 爱情/剧情/同性/
1198 
dcp_size 85.13 GB
1199 
color_space XYZ
1200 
film_scope Scope 2.39
1201 
film_title 无法触碰都爱[Doushitemo furetakunai]
1202 
caption_time 别着急，还木有出来呢～～
1203 
film_duration 01:40:14
1204 
macro_format JPEG 2000
1205 
dcp_name ""
1206 
language_version 日语/译制
1207 
film_track 5.1
1208 
long_biao 暂无
1209 
********************************************************************************
1210 
film_type 剧情/
1211 
dcp_size 108.14 GB
1212 
color_space XYZ
1213 
film_scope Scope 2.39
1214 
film_title 咖啡风暴[Coffee]
1215 
caption_time 01:48:48
1216 
film_duration 01:53:33
1217 
macro_format JPEG 2000
1218 
dcp_name ""
1219 
language_version 国语
1220 
film_track 5.1
1221 
long_biao 暂无
1222 
********************************************************************************
1223 
film_type 剧情/
1224 
dcp_size 82.4 GB
1225 
color_space XYZ
1226 
film_scope Scope 2.39
1227 
film_title 丢心[LOST CONSCIENCE]
1228 
caption_time 别着急，还木有出来呢～～
1229 
film_duration 01:43:15
1230 
macro_format JPEG 2000
1231 
dcp_name ""
1232 
language_version 国语
1233 
film_track 5.1
1234 
long_biao 暂无
1235 
********************************************************************************
1236 
film_type 动画/儿童/奇幻/
1237 
dcp_size 80.08 GB
1238 
color_space XYZ
1239 
film_scope Flat 1.85
1240 
film_title 咕噜咕噜美人鱼2[Gulu Mermaid 2]
1241 
caption_time 01:29:50
1242 
film_duration 01:33:16
1243 
macro_format JPEG 2000
1244 
dcp_name ""
1245 
language_version 国语
1246 
film_track 5.1
1247 
long_biao 暂无
1248 
********************************************************************************
1249 
film_type 奇幻/喜剧/
1250 
dcp_size 153.85 GB
1251 
color_space XYZ
1252 
film_scope Scope 2.39
1253 
film_title 二代妖精之今生有幸[Hanson and the Beast]
1254 
caption_time 01:45:24
1255 
film_duration 01:51:41
1256 
macro_format JPEG 2000
1257 
dcp_name ""
1258 
language_version 国语
1259 
film_track 5.1
1260 
long_biao 暂无
1261 
********************************************************************************
1262 
film_type 家庭/喜剧/
1263 
dcp_size 115.66 GB
1264 
color_space XYZ
1265 
film_scope Scope 2.39
1266 
film_title 圣诞奇妙公司[Santa & Cie]
1267 
caption_time 01:33:15
1268 
film_duration 01:39:04
1269 
macro_format JPEG 2000
1270 
dcp_name ""
1271 
language_version 国语 / 原版
1272 
film_track 5.1
1273 
long_biao 暂无
1274 
********************************************************************************
1275 
film_type 动作/犯罪/剧情/
1276 
dcp_size 151.69 GB
1277 
color_space XYZ
1278 
film_scope Scope 2.39
1279 
film_title 心理罪之城市之光[The Liquidator]
1280 
caption_time 01:57:08
1281 
film_duration 02:05:25
1282 
macro_format JPEG 2000
1283 
dcp_name ""
1284 
language_version 国语
1285 
film_track 5.1
1286 
long_biao 暂无
1287 
********************************************************************************
1288 
film_type 奇幻/武侠/
1289 
dcp_size 170.26 GB
1290 
color_space XYZ
1291 
film_scope Scope 2.39
1292 
film_title 妖猫传[Legend of the Demon Cat]
1293 
caption_time 02:07:40
1294 
film_duration 02:11:01
1295 
macro_format JPEG 2000
1296 
dcp_name ""
1297 
language_version 国语
1298 
film_track 5.1
1299 
long_biao 暂无
1300 
********************************************************************************
1301 
film_type 动作/科幻/冒险/
1302 
dcp_size 186.42 GB
1303 
color_space XYZ
1304 
film_scope Scope 2.39
1305 
film_title 星球大战8：最后的绝地武士[Star Wars: The Last Jedi]
1306 
caption_time 别着急，还木有出来呢～～
1307 
film_duration 02:31:45
1308 
macro_format JPEG 2000
1309 
dcp_name ""
1310 
language_version 国语 / 英语
1311 
film_track 5.1
1312 
long_biao 暂无
1313 
********************************************************************************
1314 
film_type 剧情/
1315 
dcp_size 111 GB
1316 
color_space XYZ
1317 
film_scope Scope 2.39
1318 
film_title 天籁梦想[TheSoundofaDream]
1319 
caption_time 别着急，还木有出来呢～～
1320 
film_duration 01:26:10
1321 
macro_format JPEG 2000
1322 
dcp_name ""
1323 
language_version 普通话
1324 
film_track 5.1
1325 
long_biao 暂无
1326 
********************************************************************************
1327 
film_type 剧情/奇幻/
1328 
dcp_size 146.12 GB
1329 
color_space XYZ
1330 
film_scope Scope 2.39
1331 
film_title 解忧杂货店[NAMIYA]
1332 
caption_time 01:45:44
1333 
film_duration 01:49:59
1334 
macro_format JPEG 2000
1335 
dcp_name ""
1336 
language_version 国语 / 粤语
1337 
film_track 5.1
1338 
long_biao 暂无
1339 
********************************************************************************
1340 
film_type 喜剧/
1341 
dcp_size 119.31 GB
1342 
color_space XYZ
1343 
film_scope Scope 2.39
1344 
film_title 妖铃铃[Gold Buster]
1345 
caption_time 01:24:33
1346 
film_duration 01:29:37
1347 
macro_format JPEG 2000
1348 
dcp_name ""
1349 
language_version 国语 / 粤语
1350 
film_track 5.1
1351 
long_biao 暂无
1352 
********************************************************************************
1353 
film_type 爱情/
1354 
dcp_size 37.05 GB
1355 
color_space sRGB
1356 
film_scope Flat 1.77
1357 
film_title 我来过[I WAS HERE]
1358 
caption_time 别着急，还木有出来呢～～
1359 
film_duration 01:33:07
1360 
macro_format MPEG-2
1361 
dcp_name ""
1362 
language_version 国语
1363 
film_track 5.1
1364 
long_biao 暂无
1365 
********************************************************************************
1366 
film_type 剧情/
1367 
dcp_size 86.54 GB
1368 
color_space XYZ
1369 
film_scope Scope 2.39
1370 
film_title 十七后与青春化敌为友[Dance with Youth]
1371 
caption_time 别着急，还木有出来呢～～
1372 
film_duration 01:30:45
1373 
macro_format JPEG 2000
1374 
dcp_name ""
1375 
language_version 国语
1376 
film_track 5.1
1377 
long_biao 暂无
1378 
********************************************************************************
1379 
film_type 动画/家庭/冒险/奇幻/
1380 
dcp_size 63.36 GB
1381 
color_space XYZ
1382 
film_scope Scope 2.35
1383 
film_title 小猫巴克里[Barkley]
1384 
caption_time 01:22:43
1385 
film_duration 01:26:00
1386 
macro_format JPEG 2000
1387 
dcp_name ""
1388 
language_version 国语
1389 
film_track 5.1
1390 
long_biao 暂无
1391 
********************************************************************************
1392 
film_type 故事/
1393 
dcp_size 94.08 GB
1394 
color_space XYZ
1395 
film_scope Scope 2.39
1396 
film_title 远亲[DISTANT RELATIVE]
1397 
caption_time 别着急，还木有出来呢～～
1398 
film_duration 01:32:11
1399 
macro_format JPEG 2000
1400 
dcp_name ""
1401 
language_version 国语
1402 
film_track 5.1
1403 
long_biao 暂无
1404 
********************************************************************************
1405 
film_type 爱情/喜剧/
1406 
dcp_size 148.48 GB
1407 
color_space XYZ
1408 
film_scope Scope 2.39
1409 
film_title 前任3：再见前任[The Ex-File:The Return OF The Exes]
1410 
caption_time 01:55:34
1411 
film_duration 02:00:31
1412 
macro_format JPEG 2000
1413 
dcp_name ""
1414 
language_version 国语
1415 
film_track 5.1
1416 
long_biao 暂无
1417 
********************************************************************************
1418 
film_type
1419 
dcp_size 182.97 GB
1420 
color_space XYZ
1421 
film_scope Scope 2.39
1422 
film_title 机器之血[Bleeding Steel]
1423 
caption_time 01:43:54
1424 
film_duration 01:50:24
1425 
macro_format JPEG 2000
1426 
dcp_name ""
1427 
language_version 国语
1428 
film_track 5.1
1429 
long_biao 暂无
1430 
********************************************************************************
1431 
film_type 剧情/
1432 
dcp_size 100.32 GB
1433 
color_space XYZ
1434 
film_scope Scope 2.39
1435 
film_title “醉”佳导演[Come On， Teacher]
1436 
caption_time 别着急，还木有出来呢～～
1437 
film_duration 01:28:48
1438 
macro_format JPEG 2000
1439 
dcp_name ""
1440 
language_version 国语
1441 
film_track 5.1
1442 
long_biao 暂无
1443 
********************************************************************************
1444 
film_type 青春/校园/
1445 
dcp_size 72.64 GB
1446 
color_space XYZ
1447 
film_scope Scope 2.39
1448 
film_title 热血时代[Young Blood]
1449 
caption_time 01:34:05
1450 
film_duration 01:37:50
1451 
macro_format JPEG 2000
1452 
dcp_name ""
1453 
language_version 国语
1454 
film_track 5.1
1455 
long_biao 暂无
1456 
********************************************************************************
1457 
film_type 故事/
1458 
dcp_size 118.19 GB
1459 
color_space XYZ
1460 
film_scope Scope 2.39
1461 
film_title 爱的帕斯卡[LOVE PASCAL]
1462 
caption_time 别着急，还木有出来呢～～
1463 
film_duration 01:38:26
1464 
macro_format JPEG 2000
1465 
dcp_name ""
1466 
language_version 国语
1467 
film_track 5.1
1468 
long_biao 暂无
1469 
********************************************************************************
1470 
film_type 犯罪/惊悚/
1471 
dcp_size 99.87 GB
1472 
color_space XYZ
1473 
film_scope Flat 1.85
1474 
film_title 逃离现场[ESCAPING]
1475 
caption_time 01:22:46
1476 
film_duration 01:25:31
1477 
macro_format JPEG 2000
1478 
dcp_name ""
1479 
language_version 国语
1480 
film_track 5.1
1481 
long_biao 暂无
1482 
********************************************************************************
1483 
film_type 历史/西部/
1484 
dcp_size 126.09 GB
1485 
color_space XYZ
1486 
film_scope Scope 2.39
1487 
film_title 金珠玛米[The Chainbreakers]
1488 
caption_time 01:32:27
1489 
film_duration 01:37:30
1490 
macro_format JPEG 2000
1491 
dcp_name ""
1492 
language_version 国语
1493 
film_track 5.1
1494 
long_biao 暂无
1495 
********************************************************************************
1496 
film_type 剧情/
1497 
dcp_size 128.15 GB
1498 
color_space XYZ
1499 
film_scope Flat 1.85
1500 
film_title 老兽[Old Beast]
1501 
caption_time 01:47:33
1502 
film_duration 01:50:55
1503 
macro_format JPEG 2000
1504 
dcp_name ""
1505 
language_version 国语
1506 
film_track 5.1
1507 
long_biao 暂无
1508 
********************************************************************************
1509 
film_type 惊悚/恐怖/
1510 
dcp_size 57.53 GB
1511 
color_space XYZ
1512 
film_scope Scope 2.39
1513 
film_title 惊魂七夜[SENEN FRIGHT NIGHTS]
1514 
caption_time 01:30:02
1515 
film_duration 01:31:33
1516 
macro_format JPEG 2000
1517 
dcp_name ""
1518 
language_version 国语
1519 
film_track 5.1
1520 
long_biao 暂无
1521 
********************************************************************************
1522 
film_type 惊悚/恐怖/
1523 
dcp_size 84.27 GB
1524 
color_space XYZ
1525 
film_scope Scope 2.39
1526 
film_title 墨玉太极[JADE OF TAI CHI]
1527 
caption_time 01:31:06
1528 
film_duration 01:33:23
1529 
macro_format JPEG 2000
1530 
dcp_name ""
1531 
language_version 国语
1532 
film_track 5.1
1533 
long_biao 暂无
1534 
********************************************************************************
1535 
film_type 爱情/剧情/
1536 
dcp_size 46.21 GB
1537 
color_space sRGB
1538 
film_scope Flat 1.77
1539 
film_title 悔恨[Lose Love Forever]
1540 
caption_time 01:53:22
1541 
film_duration 01:56:09
1542 
macro_format MPEG-2
1543 
dcp_name ""
1544 
language_version 国语
1545 
film_track 5.1
1546 
long_biao 暂无
1547 
********************************************************************************
1548 
film_type 动作/奇幻/武侠/
1549 
dcp_size 188.41 GB
1550 
color_space XYZ
1551 
film_scope Flat 1.85
1552 
film_title 奇门遁甲[The Thousand Faces of Dun jia]
1553 
caption_time 01:44:45
1554 
film_duration 01:52:39
1555 
macro_format JPEG 2000
1556 
dcp_name ""
1557 
language_version 国语
1558 
film_track 5.1
1559 
long_biao 暂无
1560 
********************************************************************************
1561 
film_type 爱情/剧情/喜剧/
1562 
dcp_size 118.09 GB
1563 
color_space XYZ
1564 
film_scope Flat 1.85
1565 
film_title 假如王子睡着了[The Dreaming Man]
1566 
caption_time 01:36:16
1567 
film_duration 01:41:23
1568 
macro_format JPEG 2000
1569 
dcp_name ""
1570 
language_version 国语
1571 
film_track 5.1
1572 
long_biao 暂无
1573 
********************************************************************************
1574 
film_type 剧情/
1575 
dcp_size 146.67 GB
1576 
color_space XYZ
1577 
film_scope Scope 2.39
1578 
film_title 帕丁顿熊2[Paddington 2]
1579 
caption_time 01:36:56
1580 
film_duration 01:43:30
1581 
macro_format JPEG 2000
1582 
dcp_name ""
1583 
language_version 国语 / 原版
1584 
film_track 5.1
1585 
long_biao 暂无
1586 
********************************************************************************
1587 
film_type 动作/犯罪/惊悚/
1588 
dcp_size 95.41 GB
1589 
color_space XYZ
1590 
film_scope Scope 2.39
1591 
film_title 双面劫匪[Heist]
1592 
caption_time 01:26:31
1593 
film_duration 01:31:53
1594 
macro_format JPEG 2000
1595 
dcp_name ""
1596 
language_version 国语 / 原版
1597 
film_track 5.1
1598 
long_biao 暂无
1599 
********************************************************************************
1600 
film_type 惊悚/剧情/冒险/
1601 
dcp_size 85.2 GB
1602 
color_space XYZ
1603 
film_scope Scope 2.39
1604 
film_title 鲨海[47 Meters Down]
1605 
caption_time 01:23:57
1606 
film_duration 01:28:59
1607 
macro_format JPEG 2000
1608 
dcp_name ""
1609 
language_version 国语 / 原版
1610 
film_track 5.1
1611 
long_biao 暂无
1612 
********************************************************************************
1613 
film_type 警匪/
1614 
dcp_size 165.72 GB
1615 
color_space XYZ
1616 
film_scope Scope 2.39
1617 
film_title 巨额来电[The Big Call]
1618 
caption_time 01:59:10
1619 
film_duration 02:04:43
1620 
macro_format JPEG 2000
1621 
dcp_name ""
1622 
language_version 国语
1623 
film_track 5.1
1624 
long_biao 暂无
1625 
********************************************************************************
1626 
film_type 传记/动画/犯罪/剧情/
1627 
dcp_size 117.08 GB
1628 
color_space XYZ
1629 
film_scope Flat 1.85
1630 
film_title 至爱梵高·星空之谜[Loving Vincent]
1631 
caption_time 01:31:11
1632 
film_duration 01:34:15
1633 
macro_format JPEG 2000
1634 
dcp_name ""
1635 
language_version 国语 / 原版
1636 
film_track 5.1
1637 
long_biao 暂无
1638 
********************************************************************************
1639 
film_type 传记/剧情/灾难/
1640 
dcp_size 136.99 GB
1641 
color_space XYZ
1642 
film_scope Scope 2.39
1643 
film_title 勇往直前[Only the Brave]
1644 
caption_time 01:58:57
1645 
film_duration 02:06:35
1646 
macro_format JPEG 2000
1647 
dcp_name ""
1648 
language_version 国语 / 原版
1649 
film_track 5.1
1650 
long_biao 暂无
1651 
********************************************************************************
1652 
film_type 动作/喜剧/
1653 
dcp_size 99.45 GB
1654 
color_space XYZ
1655 
film_scope Scope 2.39
1656 
film_title 疯狂特警队[Raid Dingue]
1657 
caption_time 01:42:27
1658 
film_duration 01:46:31
1659 
macro_format JPEG 2000
1660 
dcp_name ""
1661 
language_version 国语 / 原版
1662 
film_track 5.1
1663 
long_biao 暂无
1664 
********************************************************************************
1665 
film_type 剧情/喜剧/
1666 
dcp_size 124.43 GB
1667 
color_space XYZ
1668 
film_scope Scope 2.39
1669 
film_title 相声大电影之我要幸福
1670 
caption_time 01:28:44
1671 
film_duration 01:32:02
1672 
macro_format JPEG 2000
1673 
dcp_name ""
1674 
language_version 国语
1675 
film_track 5.1
1676 
long_biao 暂无
1677 
********************************************************************************
1678 
film_type 犯罪/喜剧/
1679 
dcp_size 120.52 GB
1680 
color_space XYZ
1681 
film_scope Scope 2.39
1682 
film_title 夺金四贱客[Four Against the Bank]
1683 
caption_time 01:28:55
1684 
film_duration 01:35:35
1685 
macro_format JPEG 2000
1686 
dcp_name ""
1687 
language_version 国语 / 原版
1688 
film_track 5.1
1689 
long_biao 暂无
1690 
********************************************************************************
1691 
film_type 动作/战争/
1692 
dcp_size 169.41 GB
1693 
color_space XYZ
1694 
film_scope Scope 2.39
1695 
film_title 维京：王者之战[Viking]
1696 
caption_time 01:59:30
1697 
film_duration 02:08:06
1698 
macro_format JPEG 2000
1699 
dcp_name ""
1700 
language_version 国语 / 原版
1701 
film_track 5.1
1702 
long_biao 暂无
1703 
********************************************************************************
1704 
film_type 爱情/剧情/
1705 
dcp_size 37.05 GB
1706 
color_space 709
1707 
film_scope Flat 1.77
1708 
film_title 我来过
1709 
caption_time 别着急，还木有出来呢～～
1710 
film_duration 01:33:07
1711 
macro_format MPEG-2
1712 
dcp_name ""
1713 
language_version 普通话
1714 
film_track 5.1
1715 
long_biao 暂无
1716 
********************************************************************************
1717 
film_type 剧情/犯罪/冒险
1718 
dcp_size 111.07 GB
1719 
color_space XYZ
1720 
film_scope Scope 2.39
1721 
film_title 大秦直道[THE GREAT QINZHIDAO]
1722 
caption_time 01:27:08
1723 
film_duration 01:29:35
1724 
macro_format JPEG 2000
1725 
dcp_name ""
1726 
language_version 普通话
1727 
film_track 5.1
1728 
long_biao 暂无

+ 222 - 0
rov8.py
查看文件 

@ -0,0 +1,222 @@
1 
#!/usr/bin/env python
2 
# coding: utf-8
3
4 
import base64
5 
import json
6 
from time import strftime, localtime
7
8 
import urllib2
9 
import requests
10 
from bs4 import BeautifulSoup
11 
from lxml import etree
12 
import time
13 
import mysql
14
15 
"""
16 
2、 然后获取http://www.rov8.com/index.php/Times/index/p/number.html所有的详情url。（注意是分页）
17 
3、 获取字幕报页面我们想要的信息，然后抓取出来。
18 
4、 将获取的字段存储到mysql中。
19
20 
所需字段
21 
1、片名 film_title
22 
2  出字幕时间　caption_time
23 
3、影片时长 film_duration
24 
4、影片类型 film_type
25 
5、语言版本 language_version
26 
6、编码格式 macro_format
27 
7、DCP包大小 scp_size
28 
"""
29
30 
# 模拟浏览器的访问
31 
req_header = {'User-Agent': 'Mozilla/5.0 (Macintosh;'
32 
                                ' Intel Mac OS X 10_11_6) '
33 
                                'AppleWebKit/537.36 (KHTML, like Gecko)'
34 
                                ' Chrome/59.0.3071.115 Safari/537.36'}
35
36 
class ROV:
37 
    def __init__(self):
38 
        self.base_url = 'http://www.rov8.com/index.php/Times/index/p/'
39 
        self.req_header = req_header
40 
        self.mysql = mysql.Mysql()
41
42 
    # 获取当前时间
43 
    def getCurrentTime(self):
44 
        return time.strftime('[%Y-%m-%d %H:%M:%S]', time.localtime(time.time()))
45
46 
    # 获取当前时间
47 
    def getCurrentDate(self):
48 
        return time.strftime('%Y-%m-%d', time.localtime(time.time()))
49
50
51 
    def getHtml(self, targetUrl):
52 
        req = urllib2.Request(targetUrl, "", headers=req_header)
53 
        response = urllib2.urlopen(req)
54 
        return response.read().decode('utf-8')
55
56 
    def getContents(self, pageNum):
57 
        """将传来的页码中每一个具体影片的url提取出来"""
58 
        url = self.base_url + str(pageNum) + '.html'
59 
        html = urllib2.urlopen(url)
60 
        #将网页内容转码为utf-8
61 
        htmldata = html.read().decode('utf-8')
62 
        detailPath = etree.HTML(htmldata)
63 
        urls = detailPath.xpath('//div[@class="content-zw"]/ul/li/a/@href')
64 
        for url in urls:
65 
            self.getDetailPage('http://www.rov8.com/' + url)
66
67 
    def getDetailPage(self, getDetailPageUrl):
68 
        """
69 
        通过传来的具体影片的url，获取详情页的主要信息
70 
        """
71 
        htmldata = self.getHtml(getDetailPageUrl)
72 
        soup = BeautifulSoup(htmldata, 'lxml')
73 
        film_title = soup.find('td', attrs={"class": "Atitle"}).get_text()
74 
        div = soup.find('div', attrs={"class": "art-cnt"}).get_text().encode("utf-8")
75 
        self.getFiled(div, film_title)
76
77 
    def getCaptionTimeByFilmTitle(self, film_name):
78 
        """
79 
        不用登录，通过影片名称获取出字幕时间
80 
        """
81 
        filmName = self.subString(film_name)
82 
        todaytime = strftime("%Y-%m-%d", localtime())
83 
        salt = "FYZS_sub|" + filmName + "|" + todaytime
84 
        searchcode = base64.encodestring(base64.encodestring(salt))
85 
        url = "http://www.rov8.com/fy/API.php?a=rov2018&b=GFYZS&c=skm&d=" + searchcode
86 
        r = requests.get(url)
87 
        date = base64.decodestring(base64.decodestring(r.text))
88 
        info = json.loads(date)[0]
89 
        captionTime = info[2][:8]
90 
        result = ""
91 
        if captionTime[0] != "0":
92 
            result = u'别着急，还木有出来呢～～'
93 
        else:
94 
            result = captionTime
95 
        return result
96
97 
    def getFiled(self, div, film_title):
98 
        """
99 
        通过传来的参数将所需字段过滤出来
100 
        """
101 
        captionTime = self.getCaptionTimeByFilmTitle(film_title)
102 
        caption_time = '出字幕时间：'.decode('utf-8') + captionTime
103 
        film_name = '影片名称：'.decode('utf-8') + film_title
104 
        long_biao = '龙标：'.decode('utf-8') + '暂无'
105 
        dcp_name = 'DCP包名称：""'
106 
        results = []
107 
        datalist = div.splitlines()
108 
        for j in range(0, len(datalist)):
109 
            str = datalist[j].strip()
110 
            if len(str) != 0:
111 
                nPos = str.find(' ')
112 
                if nPos == -1:
113 
                    nPos = len(str)
114 
                results.append(str[0:nPos])
115
116 
        # 从抓取的div中找到所需的字段值
117 
        rlists = []
118 
        rlists.append(film_name)
119 
        rlists.append(caption_time)
120
121 
        for str in results:
122 
            if str.find('影片时长') != -1 and len(str) < 24:
123 
                rlists.append(str)
124 
            elif str.find('影片类型') != -1:
125 
                rlists.append(str)
126 
            elif str.find('语言版本') != -1:
127 
                if len(str) < 16:
128 
                    rlists.append('语言版本：无')
129 
                else:
130 
                    rlists.append(str)
131 
            elif str.find('编码格式') != -1:
132 
                rlists.append(str)
133 
            elif str.find('影片画幅') != -1:
134 
                rlists.append(str)
135 
            elif str.find('色彩空间') != -1:
136 
                rlists.append(str)
137 
            elif str.find('影片声道') != -1:
138 
                rlists.append(str)
139 
            elif str.find('DCP包大小') != -1:
140 
                rlists.append(str)
141 
                break
142 
            else:
143 
                pass
144 
        rlists.append(dcp_name)
145 
        rlists.append(long_biao)
146 
        print '*' * 80
147 
        # for i in rlists:
148 
        #     print i
149 
        self.list2dict(rlists)
150
151
152 
    def list2dict(self, lists):
153 
        """
154 
        将列表转化为字典，方便mysql插入
155 
        """
156 
        tmp1 = []
157 
        tmp2 = []
158 
        for i in range(len(lists)):
159 
            if i == 0:
160 
                tmp1.append('film_title')
161 
                tmp2.append(lists[i][5:])
162 
            elif i == 1:
163 
                tmp1.append('caption_time')
164 
                tmp2.append(lists[i][6:])
165 
            elif i == 2:
166 
                tmp1.append('film_duration')
167 
                tmp2.append(lists[i][15:])
168 
            elif i == 3:
169 
                tmp1.append('film_scope')
170 
                tmp2.append(lists[i][15:])
171 
            elif i == 4:
172 
                tmp1.append('film_type')
173 
                tmp2.append(lists[i][15:])
174 
            elif i == 5:
175 
                tmp1.append('language_version')
176 
                tmp2.append(lists[i][15:])
177 
            elif i == 6:
178 
                tmp1.append('color_space')
179 
                tmp2.append(lists[i][15:])
180 
            elif i == 7:
181 
                tmp1.append('film_track')
182 
                tmp2.append(lists[i][15:])
183 
            elif i == 8:
184 
                tmp1.append('macro_format')
185 
                tmp2.append(lists[i][15:])
186 
            elif i == 9:
187 
                tmp1.append('dcp_size')
188 
                tmp2.append(lists[i][15:])
189 
            elif i == 10:
190 
                tmp1.append('dcp_name')
191 
                tmp2.append(lists[i][15:])
192 
            elif i == 11:
193 
                tmp1.append('long_biao')
194 
                tmp2.append("暂无")
195 
            else:
196 
                pass
197
198 
        result_dict = dict(zip(tmp1, tmp2))
199 
        self.mysql.dealData(result_dict)
200 
        for k, v in result_dict.items():
201 
            print k, v
202
203 
    def subString(self, filmTitle):
204 
        """
205 
        去掉电影名称中的中括号[]
206 
        """
207 
        film_name = ""
208 
        if filmTitle.find('[') != -1:
209 
            index = filmTitle.index('[')
210 
            film_name = filmTitle[:index]
211 
        else:
212 
            film_name = filmTitle
213 
        return film_name
214
215 
    def main(self):
216 
        self.getContents(1)
217 
        # for i in range(26):
218 
        # 	self.getContents(i+1)
219
220 
if __name__ == '__main__':
221 
    rov = ROV()
222 
    rov.main()

+ 140 - 0
taopp.py
查看文件 

@ -0,0 +1,140 @@
1 
#!/usr/bin/env python
2 
# coding: utf-8
3
4 
import urllib2
5 
import urllib
6 
import requests
7 
from bs4 import BeautifulSoup
8 
from lxml import etree
9 
import MySQLdb
10 
import time
11 
import random
12 
import sys
13 
reload(sys)
14 
sys.setdefaultencoding('utf8')
15
16 
"""猫眼不需要http请求的头部信息，添加上反而会出错"""
17 
class TaoPP():
18 
    # 获取当前时间
19 
    def getCurrentTime(self):
20 
        return time.strftime('[%Y-%m-%d %H:%M:%S]', time.localtime(time.time()))
21 
    def __init__(self):
22 
        self.time = time
23 
        try:
24 
            #self.db = MySQLdb.connect('127.0.0.1', 'flyer_user', 'Tu4a0X9hOPKz6jS!e', 'flyer_db',22809)
25 
            self.db =  MySQLdb.connect('rm-2zeqhsdou4zxl4914.mysql.rds.aliyuncs.com', 'flyer_user', 'GLZcMigd4VnsrmzNrOC1HGjv2eQzBqg3', 'flyer_db', 3306)
26 
            self.cur = self.db.cursor()
27 
        except MySQLdb.Error, e:
28 
            print self.getCurrentTime(), "连接数据库错误，原因%d: %s" % (e.args[0], e.args[1])
29
30 
    # 插入数据
31 
    def insertData(self, my_dict):
32 
        try:
33 
            self.db.set_character_set('utf8')
34 
            cols = ', '.join(my_dict.keys())
35 
            print cols
36 
            values = '","'.join(my_dict.values())
37 
            print values
38 
            sql = "INSERT INTO  taopp (%s) VALUES (%s)" % (cols, '"' + values + '"')
39 
            try:
40 
                result = self.cur.execute(sql)
41 
                insert_id = self.db.insert_id()
42 
                self.db.commit()
43 
                # 判断是否执行成功
44 
                if result:
45 
                    return insert_id
46 
                else:
47 
                    return 0
48 
            except MySQLdb.Error, e:
49 
                # 发生错误时回滚
50 
                self.db.rollback()
51 
                # 主键唯一，无法插入
52 
                if "key 'PRIMARY'" in e.args[1]:
53 
                    print self.getCurrentTime(), "数据已存在，未插入数据"
54 
                else:
55 
                    print self.getCurrentTime(), "插入数据失败，原因 %d: %s" % (e.args[0], e.args[1])
56 
        except MySQLdb.Error, e:
57 
            print self.getCurrentTime(), "数据库错误，原因%d: %s" % (e.args[0], e.args[1])
58 
            # self.db.close
59
60 
    def dealData(self, my_dict):
61 
        """先从数据库中查询这个影片名的记录，如果没有直接插入；
62 
        若是数据库中已经存在数据，那么什么都不做"""
63 
        self.db.set_character_set('utf8')
64 
        filmTitile = my_dict.get('film_title')
65 
        result = self.findFilmByfilmTitle(filmTitile)
66 
        if len(result) == 0:
67 
            self.insertData(my_dict)
68 
            return
69 
        else:
70 
            pass
71
72
73 
    def findFilmByfilmTitle(self, filmTitile):
74 
        """通过影片名称去数据库中查询"""
75 
        self.db.set_character_set('utf8')
76 
        sql = "select * from taopp where film_title='%s'" % (filmTitile)
77 
        self.cur.execute(sql)
78 
        results = self.cur.fetchall()
79 
        self.db.commit()
80 
        return results
81
82 
    def getHtml(self,url):
83 
        """获取html"""
84 
        req = urllib2.Request(url)
85 
        html = urllib2.urlopen(req).read().decode('utf-8')
86 
        # print html
87 
        return html
88
89 
    def get_detail_url(self, targetUrl):
90 
        """从概览页面中去获取剧透影片的详情页面"""
91 
        html = self.getHtml(targetUrl)
92 
        detailPath = etree.HTML(html)
93 
        detail_urls = detailPath.xpath(r'/html/body/div[4]/div[1]/div[2]/div[1]/div/a[1]/@href')
94 
        others_urls = detailPath.xpath(r'/html/body/div[4]/div[1]/div[2]/div[2]/div/a[1]/@href')
95
96 
        for url in others_urls:
97 
            # print url
98 
            self.getContents(url)
99
100 
        for url in detail_urls:
101 
            self.getContents(url)
102 
            # print url
103
104 
    def getContents(self, url):
105 
        tmp1 = []
106 
        tmp2 = []
107 
        html = self.getHtml(url)
108 
        detailPath = etree.HTML(html)
109
110 
        film_title = detailPath.xpath('/html/body/div[3]/div[4]/div/h3/text()')
111 
        for name in film_title:
112 
            # print name
113 
            tmp1.append('film_title')
114 
            tmp2.append(name)
115 
            if len(name) != 0:
116 
                break
117
118 
        pic_url = detailPath.xpath('/html/body/div[3]/div[4]/div/div[1]/img/@src')
119 
        for pu in pic_url:
120 
            # print pu
121 
            tmp1.append('pic_url')
122 
            tmp2.append(pu)
123
124 
        release_time = detailPath.xpath('/html/body/div[3]/div[4]/div/div[2]/text()')
125 
        for rt in release_time:
126 
            # print rt[5:]
127 
            tmp1.append('release_time')
128 
            tmp2.append(rt[5:15])
129
130 
        result_dict = dict(zip(tmp1, tmp2))
131 
        # self.time.sleep(1)
132 
        self.dealData(result_dict)
133 
        print '**' * 20
134 
        for k, v in result_dict.items():
135 
            print k, v
136
137
138 
if __name__ == '__main__':
139 
    taopp = TaoPP()
140 
    taopp.get_detail_url('https://dianying.taobao.com/showList.htm?spm=a1z21.3046609.header.4.bpD8SA&n_s=new')