├── .DS_Store ├── .gitignore ├── LICENSE ├── README.md ├── mysql ├── __init__.py ├── items.py ├── middlewares.py ├── pipelines.py ├── settings.py └── spiders │ ├── __init__.py │ ├── musicspider.py │ ├── run.py │ └── videospider.py └── scrapy.cfg /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yanceyblog/scrapy-mysql/f426eaa94e87961cfcc9b35bb1108f6da24cbf5b/.DS_Store -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | 27 | # PyInstaller 28 | # Usually these files are written by a python script from a template 29 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 30 | *.manifest 31 | *.spec 32 | 33 | # Installer logs 34 | pip-log.txt 35 | pip-delete-this-directory.txt 36 | 37 | # Unit test / coverage reports 38 | htmlcov/ 39 | .tox/ 40 | .coverage 41 | .coverage.* 42 | .cache 43 | nosetests.xml 44 | coverage.xml 45 | *,cover 46 | .hypothesis/ 47 | 48 | # Translations 49 | *.mo 50 | *.pot 51 | 52 | # Django stuff: 53 | *.log 54 | local_settings.py 55 | 56 | # Flask stuff: 57 | instance/ 58 | .webassets-cache 59 | 60 | # Scrapy stuff: 61 | .scrapy 62 | 63 | # Sphinx documentation 64 | docs/_build/ 65 | 66 | # PyBuilder 67 | target/ 68 | 69 | # IPython Notebook 70 | .ipynb_checkpoints 71 | 72 | # pyenv 73 | .python-version 74 | 75 | # celery beat schedule file 76 | celerybeat-schedule 77 | 78 | # dotenv 79 | .env 80 | 81 | # virtualenv 82 | venv/ 83 | ENV/ 84 | 85 | # Spyder project settings 86 | .spyderproject 87 | 88 | # Rope project settings 89 | .ropeproject 90 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # 爬虫数据存储实例 2 | [TOC] 3 | 4 | > 本章将实现数据存储到数据库的实例。博客地址http://blog.csdn.net/yancey_blog/article/details/53895821 5 | 6 | ## 数据存储 7 | scrapy支持将数据存储到文件,例如csv、jl、jsonlines、pickle、marshal、json、xml，少量的数据存储到数据库还行，如果超大量的数据存储到文件（当然图片还是要存文件的），就显得不太友好，毕竟这些数据要为我所用。 8 | 9 | 因此我们通常将数据存储到数据库，本处将介绍的是最常用的数据库mysql。我们也看到scrapy中的pipeline文件还没有用到，其实这个文件就是处理spider分发下来的item，我们可以在pipeline中处理文件的存储。 10 | 11 | * mysql库(PyMysql)的添加 12 | 13 | 打开pycharm File-->Default Settings-->Project interpreter点击左下角的“+”，搜索PyMysql，如图： 14 | 15 | 16 | 17 | 点击安装install package，如果无法安装可以选择将上面的install to user‘s site...勾选安装到Users目录下。 18 | 19 | ## 配置mysql服务 20 | 21 | 1、安装mysql 22 | 23 | ``` 24 | root@ubuntu:~# sudo apt-get install mysql-server 25 | ``` 26 | 27 | ``` 28 | root@ubuntu:~# apt isntall mysql-client 29 | ``` 30 | 31 | ``` 32 | root@ubuntu:~# apt install libmysqlclient-dev 33 | ``` 34 | 35 | 期间会弹出设置root账户的密码框，输入两次相同密码。 36 | 37 | 38 | ---------- 39 | 40 | 41 | 2、查询是否安装成功 42 | 43 | ``` 44 | root@ubuntu:~# sudo netstat -tap | grep mysql 45 | ``` 46 | 47 | ```shell 48 | root@ubuntu:~# netstat -tap | grep mysql 49 | 50 | tcp6 0 0 [::]:mysql [::]:* LISTEN 7510/mysqld 51 | ``` 52 | 53 | 54 | ---------- 55 | 56 | 57 | 3、开启远程访问mysql 58 | 59 | * 编辑mysql配置文件，注释掉“bind-address = 127.0.0.1” 60 | 61 | ``` 62 | root@ubuntu:~# vi /etc/mysql/mysql.conf.d/mysqld.cnf 63 | ``` 64 | 65 | ``` 66 | #bind-address = 127.0.0.1 67 | ``` 68 | 69 | * 进入mysql root账户 70 | 71 | ``` 72 | root@ubuntu:~# mysql -u root -p123456 73 | ``` 74 | 75 | * 在mysql环境中输入grant all on *.* to username@'%' identified by 'password'; 76 | * 或者grant all on *.* to username@'%' identified by 'password' with grand option; 77 | 78 | ``` 79 | root@ubuntu:~# grant all on *.* to china@'%' identified by '123456'; 80 | ``` 81 | 82 | * 刷新flush privileges;然后重启mysql，通过/etc/init.d/mysql restart命令 83 | 84 | ``` 85 | root@ubuntu:~# flush privileges; 86 | ``` 87 | ``` 88 | root@ubuntu:~# /etc/init.d/mysql restart 89 | ``` 90 | 91 | * 远程连接时客户端设置： 92 | 93 | > 94 | 95 | ---------- 96 | 4、常见问题 97 | 98 | - 1045 access denied for user 'root'@'localhost(ip)' using password yes 99 | 100 | 101 | ``` 102 | 1、mysql -u root -p; 103 | 2、GRANT ALL PRIVILEGES ON *.* TO 'myuser'@'%' IDENTIFIED BY 'mypassword' WITH GRANT OPTION; 104 | 3、FLUSH PRIVILEGES; 105 | ``` 106 | 107 | 108 | ---------- 109 | ## 在mysql中创建好四个item表 110 | 111 | 112 | 113 | ## 创建项目 114 | 115 | 安装好PyMysql后就可以在pipeline中处理存储的逻辑了。首先创建项目：`scrapy startproject mysql` 本例还是使用上一章多个爬虫组合实例的例子，处理将其中四个item存储到mysql数据库。 116 | 然后打开创建好的mysql项目，在settings.py中添加数据库连接相关的常量。 117 | 118 | ```python 119 | # -*- coding: utf-8 -*- 120 | BOT_NAME = 'mysql' 121 | 122 | SPIDER_MODULES = ['mysql.spiders'] 123 | NEWSPIDER_MODULE = 'mysql.spiders' 124 | 125 | MYSQL_HOST = 'localhost' 126 | MYSQL_DBNAME = 'spider' 127 | MYSQL_USER = 'root' 128 | MYSQL_PASSWD = '123456' 129 | 130 | DOWNLOAD_DELAY = 1 131 | 132 | ITEM_PIPELINES = { 133 | 'mysql.pipelines.DoubanPipeline': 301, 134 | } 135 | ``` 136 | 137 | pipeline.py配置 138 | 139 | 140 | ```python 141 | # -*- coding: utf-8 -*- 142 | 143 | # Define your item pipelines here 144 | # 145 | # Don't forget to add your pipeline to the ITEM_PIPELINES setting 146 | # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html 147 | import pymysql 148 | from scrapy import log 149 | 150 | from mysql import settings 151 | from mysql.items import MusicItem, MusicReviewItem, VideoItem, VideoReviewItem 152 | 153 | 154 | class DoubanPipeline(object): 155 | def __init__(self): 156 | self.connect = pymysql.connect( 157 | host=settings.MYSQL_HOST, 158 | db=settings.MYSQL_DBNAME, 159 | user=settings.MYSQL_USER, 160 | passwd=settings.MYSQL_PASSWD, 161 | charset='utf8', 162 | use_unicode=True) 163 | self.cursor = self.connect.cursor() 164 | 165 | def process_item(self, item, spider): 166 | if item.__class__ == MusicItem: 167 | try: 168 | self.cursor.execute("""select * from music_douban where music_url = %s""", item["music_url"]) 169 | ret = self.cursor.fetchone() 170 | if ret: 171 | self.cursor.execute( 172 | """update music_douban set music_name = %s,music_alias = %s,music_singer = %s, 173 | music_time = %s,music_rating = %s,music_votes = %s,music_tags = %s,music_url = %s 174 | where music_url = %s""", 175 | (item['music_name'], 176 | item['music_alias'], 177 | item['music_singer'], 178 | item['music_time'], 179 | item['music_rating'], 180 | item['music_votes'], 181 | item['music_tags'], 182 | item['music_url'], 183 | item['music_url'])) 184 | else: 185 | self.cursor.execute( 186 | """insert into music_douban(music_name,music_alias,music_singer,music_time,music_rating, 187 | music_votes,music_tags,music_url) 188 | value (%s,%s,%s,%s,%s,%s,%s,%s)""", 189 | (item['music_name'], 190 | item['music_alias'], 191 | item['music_singer'], 192 | item['music_time'], 193 | item['music_rating'], 194 | item['music_votes'], 195 | item['music_tags'], 196 | item['music_url'])) 197 | self.connect.commit() 198 | except Exception as error: 199 | log(error) 200 | return item 201 | 202 | elif item.__class__ == MusicReviewItem: 203 | try: 204 | self.cursor.execute("""select * from music_review_douban where review_url = %s""", item["review_url"]) 205 | ret = self.cursor.fetchone() 206 | if ret: 207 | self.cursor.execute( 208 | """update music_review_douban set review_title = %s,review_content = %s,review_author = %s, 209 | review_music = %s,review_time = %s,review_url = %s 210 | where review_url = %s""", 211 | (item['review_title'], 212 | item['review_content'], 213 | item['review_author'], 214 | item['review_music'], 215 | item['review_time'], 216 | item['review_url'], 217 | item['review_url'])) 218 | else: 219 | self.cursor.execute( 220 | """insert into music_review_douban(review_title,review_content,review_author,review_music,review_time, 221 | review_url) 222 | value (%s,%s,%s,%s,%s,%s)""", 223 | (item['review_title'], 224 | item['review_content'], 225 | item['review_author'], 226 | item['review_music'], 227 | item['review_time'], 228 | item['review_url'])) 229 | self.connect.commit() 230 | except Exception as error: 231 | log(error) 232 | return item 233 | 234 | elif item.__class__ == VideoItem: 235 | try: 236 | self.cursor.execute("""select * from video_douban where video_url = %s""", item["video_url"]) 237 | ret = self.cursor.fetchone() 238 | if ret: 239 | self.cursor.execute( 240 | """update video_douban set video_name= %s,video_alias= %s,video_actor= %s,video_year= %s, 241 | video_time= %s,video_rating= %s,video_votes= %s,video_tags= %s,video_url= %s, 242 | video_director= %s,video_type= %s,video_bigtype= %s,video_area= %s,video_language= %s, 243 | video_length= %s,video_writer= %s,video_desc= %s,video_episodes= %s where video_url = %s""", 244 | (item['video_name'], 245 | item['video_alias'], 246 | item['video_actor'], 247 | item['video_year'], 248 | item['video_time'], 249 | item['video_rating'], 250 | item['video_votes'], 251 | item['video_tags'], 252 | item['video_url'], 253 | item['video_director'], 254 | item['video_type'], 255 | item['video_bigtype'], 256 | item['video_area'], 257 | item['video_language'], 258 | item['video_length'], 259 | item['video_writer'], 260 | item['video_desc'], 261 | item['video_episodes'], 262 | item['video_url'])) 263 | else: 264 | self.cursor.execute( 265 | """insert into video_douban(video_name,video_alias,video_actor,video_year,video_time, 266 | video_rating,video_votes,video_tags,video_url,video_director,video_type,video_bigtype, 267 | video_area,video_language,video_length,video_writer,video_desc,video_episodes) 268 | value (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)""", 269 | (item['video_name'], 270 | item['video_alias'], 271 | item['video_actor'], 272 | item['video_year'], 273 | item['video_time'], 274 | item['video_rating'], 275 | item['video_votes'], 276 | item['video_tags'], 277 | item['video_url'], 278 | item['video_director'], 279 | item['video_type'], 280 | item['video_bigtype'], 281 | item['video_area'], 282 | item['video_language'], 283 | item['video_length'], 284 | item['video_writer'], 285 | item['video_desc'], 286 | item['video_episodes'])) 287 | self.connect.commit() 288 | except Exception as error: 289 | log(error) 290 | return item 291 | 292 | elif item.__class__ == VideoReviewItem: 293 | try: 294 | self.cursor.execute("""select * from video_review_douban where review_url = %s""", item["review_url"]) 295 | ret = self.cursor.fetchone() 296 | if ret: 297 | self.cursor.execute( 298 | """update video_review_douban set review_title = %s,review_content = %s,review_author = %s, 299 | review_video = %s,review_time = %s,review_url = %s 300 | where review_url = %s""", 301 | (item['review_title'], 302 | item['review_content'], 303 | item['review_author'], 304 | item['review_video'], 305 | item['review_time'], 306 | item['review_url'], 307 | item['review_url'])) 308 | else: 309 | self.cursor.execute( 310 | """insert into video_review_douban(review_title,review_content,review_author,review_video,review_time, 311 | review_url) 312 | value (%s,%s,%s,%s,%s,%s)""", 313 | (item['review_title'], 314 | item['review_content'], 315 | item['review_author'], 316 | item['review_video'], 317 | item['review_time'], 318 | item['review_url'])) 319 | self.connect.commit() 320 | except Exception as error: 321 | log(error) 322 | return item 323 | else: 324 | pass 325 | 326 | ``` 327 | 在上面的pipeline中我已经做了数据库去重的操作。 328 | 329 | ## 运行爬虫 330 | pycharm运行run.py，mysql数据库表中已经存好了我们要的数据。 331 | 332 | 333 | 334 | 335 | -------------------------------------------------------------------------------- /mysql/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/yanceyblog/scrapy-mysql/f426eaa94e87961cfcc9b35bb1108f6da24cbf5b/mysql/__init__.py -------------------------------------------------------------------------------- /mysql/items.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Define here the models for your scraped items 4 | # 5 | # See documentation in: 6 | # http://doc.org/en/latest/topics/items.html 7 | 8 | from scrapy import Item, Field 9 | 10 | 11 | # 音乐 12 | class MusicItem(Item): 13 | music_name = Field() 14 | music_alias = Field() 15 | music_singer = Field() 16 | music_time = Field() 17 | music_rating = Field() 18 | music_votes = Field() 19 | music_tags = Field() 20 | music_url = Field() 21 | 22 | 23 | # 乐评 24 | class MusicReviewItem(Item): 25 | review_title = Field() 26 | review_content = Field() 27 | review_author = Field() 28 | review_music = Field() 29 | review_time = Field() 30 | review_url = Field() 31 | 32 | 33 | # 视频 34 | class VideoItem(Item): 35 | video_name = Field() 36 | video_alias = Field() 37 | video_actor = Field() 38 | video_year = Field() 39 | video_time = Field() 40 | video_rating = Field() 41 | video_votes = Field() 42 | video_tags = Field() 43 | video_url = Field() 44 | video_director = Field() 45 | video_type = Field() 46 | video_bigtype = Field() 47 | video_area = Field() 48 | video_language = Field() 49 | video_length = Field() 50 | video_writer = Field() 51 | video_desc = Field() 52 | video_episodes = Field() 53 | 54 | 55 | # 影评 56 | class VideoReviewItem(Item): 57 | review_title = Field() 58 | review_content = Field() 59 | review_author = Field() 60 | review_video = Field() 61 | review_time = Field() 62 | review_url = Field() 63 | -------------------------------------------------------------------------------- /mysql/middlewares.py: -------------------------------------------------------------------------------- 1 | # -*-coding:utf-8-*- 2 | 3 | 4 | import random 5 | from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware 6 | 7 | 8 | class RotateUserAgentMiddleware(UserAgentMiddleware): 9 | def __init__(self, user_agent=''): 10 | self.user_agent = user_agent 11 | 12 | def process_request(self, request, spider): 13 | ua = random.choice(self.user_agent_list) 14 | if ua: 15 | # print(ua) 16 | request.headers.setdefault('User-Agent', ua) 17 | 18 | # the default user_agent_list composes chrome,I E,firefox,Mozilla,opera,netscape 19 | # for more user agent strings,you can find it in http://www.useragentstring.com/pages/useragentstring.php 20 | user_agent_list = [ \ 21 | "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" \ 22 | "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", \ 23 | "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", \ 24 | "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", \ 25 | "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", \ 26 | "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", \ 27 | "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", \ 28 | "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \ 29 | "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \ 30 | "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", \ 31 | "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \ 32 | "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", \ 33 | "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \ 34 | "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \ 35 | "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", \ 36 | "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", \ 37 | "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", \ 38 | "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" 39 | ] 40 | -------------------------------------------------------------------------------- /mysql/pipelines.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Define your item pipelines here 4 | # 5 | # Don't forget to add your pipeline to the ITEM_PIPELINES setting 6 | # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html 7 | import pymysql 8 | from scrapy import log 9 | 10 | from mysql import settings 11 | from mysql.items import MusicItem, MusicReviewItem, VideoItem, VideoReviewItem 12 | 13 | 14 | class DoubanPipeline(object): 15 | def __init__(self): 16 | self.connect = pymysql.connect( 17 | host=settings.MYSQL_HOST, 18 | db=settings.MYSQL_DBNAME, 19 | user=settings.MYSQL_USER, 20 | passwd=settings.MYSQL_PASSWD, 21 | charset='utf8', 22 | use_unicode=True) 23 | self.cursor = self.connect.cursor() 24 | 25 | def process_item(self, item, spider): 26 | if item.__class__ == MusicItem: 27 | try: 28 | self.cursor.execute("""select * from music_douban where music_url = %s""", item["music_url"]) 29 | ret = self.cursor.fetchone() 30 | if ret: 31 | self.cursor.execute( 32 | """update music_douban set music_name = %s,music_alias = %s,music_singer = %s, 33 | music_time = %s,music_rating = %s,music_votes = %s,music_tags = %s,music_url = %s 34 | where music_url = %s""", 35 | (item['music_name'], 36 | item['music_alias'], 37 | item['music_singer'], 38 | item['music_time'], 39 | item['music_rating'], 40 | item['music_votes'], 41 | item['music_tags'], 42 | item['music_url'], 43 | item['music_url'])) 44 | else: 45 | self.cursor.execute( 46 | """insert into music_douban(music_name,music_alias,music_singer,music_time,music_rating, 47 | music_votes,music_tags,music_url) 48 | value (%s,%s,%s,%s,%s,%s,%s,%s)""", 49 | (item['music_name'], 50 | item['music_alias'], 51 | item['music_singer'], 52 | item['music_time'], 53 | item['music_rating'], 54 | item['music_votes'], 55 | item['music_tags'], 56 | item['music_url'])) 57 | self.connect.commit() 58 | except Exception as error: 59 | log(error) 60 | return item 61 | 62 | elif item.__class__ == MusicReviewItem: 63 | try: 64 | self.cursor.execute("""select * from music_review_douban where review_url = %s""", item["review_url"]) 65 | ret = self.cursor.fetchone() 66 | if ret: 67 | self.cursor.execute( 68 | """update music_review_douban set review_title = %s,review_content = %s,review_author = %s, 69 | review_music = %s,review_time = %s,review_url = %s 70 | where review_url = %s""", 71 | (item['review_title'], 72 | item['review_content'], 73 | item['review_author'], 74 | item['review_music'], 75 | item['review_time'], 76 | item['review_url'], 77 | item['review_url'])) 78 | else: 79 | self.cursor.execute( 80 | """insert into music_review_douban(review_title,review_content,review_author,review_music,review_time, 81 | review_url) 82 | value (%s,%s,%s,%s,%s,%s)""", 83 | (item['review_title'], 84 | item['review_content'], 85 | item['review_author'], 86 | item['review_music'], 87 | item['review_time'], 88 | item['review_url'])) 89 | self.connect.commit() 90 | except Exception as error: 91 | log(error) 92 | return item 93 | 94 | elif item.__class__ == VideoItem: 95 | try: 96 | self.cursor.execute("""select * from video_douban where video_url = %s""", item["video_url"]) 97 | ret = self.cursor.fetchone() 98 | if ret: 99 | self.cursor.execute( 100 | """update video_douban set video_name= %s,video_alias= %s,video_actor= %s,video_year= %s, 101 | video_time= %s,video_rating= %s,video_votes= %s,video_tags= %s,video_url= %s, 102 | video_director= %s,video_type= %s,video_bigtype= %s,video_area= %s,video_language= %s, 103 | video_length= %s,video_writer= %s,video_desc= %s,video_episodes= %s where video_url = %s""", 104 | (item['video_name'], 105 | item['video_alias'], 106 | item['video_actor'], 107 | item['video_year'], 108 | item['video_time'], 109 | item['video_rating'], 110 | item['video_votes'], 111 | item['video_tags'], 112 | item['video_url'], 113 | item['video_director'], 114 | item['video_type'], 115 | item['video_bigtype'], 116 | item['video_area'], 117 | item['video_language'], 118 | item['video_length'], 119 | item['video_writer'], 120 | item['video_desc'], 121 | item['video_episodes'], 122 | item['video_url'])) 123 | else: 124 | self.cursor.execute( 125 | """insert into video_douban(video_name,video_alias,video_actor,video_year,video_time, 126 | video_rating,video_votes,video_tags,video_url,video_director,video_type,video_bigtype, 127 | video_area,video_language,video_length,video_writer,video_desc,video_episodes) 128 | value (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)""", 129 | (item['video_name'], 130 | item['video_alias'], 131 | item['video_actor'], 132 | item['video_year'], 133 | item['video_time'], 134 | item['video_rating'], 135 | item['video_votes'], 136 | item['video_tags'], 137 | item['video_url'], 138 | item['video_director'], 139 | item['video_type'], 140 | item['video_bigtype'], 141 | item['video_area'], 142 | item['video_language'], 143 | item['video_length'], 144 | item['video_writer'], 145 | item['video_desc'], 146 | item['video_episodes'])) 147 | self.connect.commit() 148 | except Exception as error: 149 | log(error) 150 | return item 151 | 152 | elif item.__class__ == VideoReviewItem: 153 | try: 154 | self.cursor.execute("""select * from video_review_douban where review_url = %s""", item["review_url"]) 155 | ret = self.cursor.fetchone() 156 | if ret: 157 | self.cursor.execute( 158 | """update video_review_douban set review_title = %s,review_content = %s,review_author = %s, 159 | review_video = %s,review_time = %s,review_url = %s 160 | where review_url = %s""", 161 | (item['review_title'], 162 | item['review_content'], 163 | item['review_author'], 164 | item['review_video'], 165 | item['review_time'], 166 | item['review_url'], 167 | item['review_url'])) 168 | else: 169 | self.cursor.execute( 170 | """insert into video_review_douban(review_title,review_content,review_author,review_video,review_time, 171 | review_url) 172 | value (%s,%s,%s,%s,%s,%s)""", 173 | (item['review_title'], 174 | item['review_content'], 175 | item['review_author'], 176 | item['review_video'], 177 | item['review_time'], 178 | item['review_url'])) 179 | self.connect.commit() 180 | except Exception as error: 181 | log(error) 182 | return item 183 | else: 184 | pass 185 | -------------------------------------------------------------------------------- /mysql/settings.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Scrapy settings for mysql project 4 | # 5 | # For simplicity, this file contains only settings considered important or 6 | # commonly used. You can find more settings consulting the documentation: 7 | # 8 | # http://doc.scrapy.org/en/latest/topics/settings.html 9 | # http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html 10 | # http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html 11 | 12 | BOT_NAME = 'mysql' 13 | 14 | SPIDER_MODULES = ['mysql.spiders'] 15 | NEWSPIDER_MODULE = 'mysql.spiders' 16 | 17 | 18 | MYSQL_HOST = 'localhost' 19 | MYSQL_DBNAME = 'spider' 20 | MYSQL_USER = 'root' 21 | MYSQL_PASSWD = '123456' 22 | 23 | DOWNLOAD_DELAY = 1 24 | 25 | ITEM_PIPELINES = { 26 | 'mysql.pipelines.DoubanPipeline': 301, 27 | 28 | } 29 | 30 | DOWNLOADER_MIDDLEWARES = { 31 | 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None, 32 | 'mysql.middlewares.RotateUserAgentMiddleware': 543, 33 | } 34 | -------------------------------------------------------------------------------- /mysql/spiders/__init__.py: -------------------------------------------------------------------------------- 1 | # This package will contain the spiders of your Scrapy project 2 | # 3 | # Please refer to the documentation for information on how to create and manage 4 | # your spiders. 5 | -------------------------------------------------------------------------------- /mysql/spiders/musicspider.py: -------------------------------------------------------------------------------- 1 | # coding:utf-8 2 | 3 | from scrapy.spider import CrawlSpider, Rule 4 | from scrapy.linkextractors import LinkExtractor 5 | from mysql.items import MusicItem, MusicReviewItem 6 | from scrapy import log 7 | 8 | import re 9 | 10 | 11 | class MusicSpider(CrawlSpider): 12 | name = 'music' 13 | allowed_domains = ['music.douban.com'] 14 | start_urls = ['https://music.douban.com/tag/', 15 | 'https://music.douban.com/tag/?view=cloud' 16 | ] 17 | rules = (Rule(LinkExtractor(allow=r"/tag/((\d+)|([\u4e00-\u9fa5]+)|(\w+))$")), 18 | Rule(LinkExtractor(allow=r"/tag/((\d+)|([\u4e00-\u9fa5]+)|(\w+))\?start=\d+\&type=T$")), 19 | Rule(LinkExtractor(allow=r"/subject/\d+/reviews\?sort=time$")), 20 | Rule(LinkExtractor(allow=r"/subject/\d+/reviews\?sort=time\&start=\d+$")), 21 | Rule(LinkExtractor(allow=r"/subject/\d+/$"), callback="parse_music", follow=True), 22 | Rule(LinkExtractor(allow=r"/review/\d+/$"), callback="parse_review", follow=True), 23 | ) 24 | 25 | def parse_music(self, response): 26 | item = MusicItem() 27 | try: 28 | item['music_name'] = response.xpath('//*[@id="wrapper"]/h1/span/text()').extract()[0] 29 | content = "".join(response.xpath('//*[@id="info"]').extract()) 30 | info = response.xpath('//*[@id="info"]/span').extract() 31 | item['music_alias'] = "" 32 | item['music_singer'] = "" 33 | item['music_time'] = "" 34 | for i in range(0, len(info)): 35 | if "又名" in info[i]: 36 | if i == 0: 37 | item['music_alias'] = response.xpath('//*[@id="info"]/text()').extract()[1] \ 38 | .replace("\xa0", "").replace("\n", "").rstrip() 39 | elif i == 1: 40 | item['music_alias'] = response.xpath('//*[@id="info"]/text()').extract()[2] \ 41 | .replace("\xa0", "").replace("\n", "").rstrip() 42 | elif i == 2: 43 | item['music_alias'] = response.xpath('//*[@id="info"]/text()').extract()[3] \ 44 | .replace("\xa0", "").replace("\n", "").rstrip() 45 | 46 | else: 47 | item['music_alias'] = "" 48 | # break 49 | if "表演者" in info[i]: 50 | if i == 0: 51 | item['music_singer'] = "|".join( 52 | response.xpath('//*[@id="info"]/span[1]/span/a/text()').extract()) 53 | elif i == 1: 54 | item['music_singer'] = "|".join( 55 | response.xpath('//*[@id="info"]/span[2]/span/a/text()').extract()) 56 | elif i == 2: 57 | item['music_singer'] = "|".join( 58 | response.xpath('//*[@id="info"]/span[3]/span/a/text()').extract()) 59 | else: 60 | item['music_singer'] = "" 61 | # break 62 | if "发行时间" in info[i]: 63 | nbsp = re.findall(r"发行时间:(.*?)
", content, re.S) 64 | item['music_time'] = "".join(nbsp).replace("\xa0", "").replace("\n", "").replace(" ", "") 65 | # break 66 | try: 67 | item['music_rating'] = "".join(response.xpath( 68 | '//*[@class="rating_self clearfix"]/strong/text()').extract()) 69 | item['music_votes'] = "".join(response.xpath( 70 | '//*[@class="rating_self clearfix"]/div/div[@class="rating_sum"]/a/span/text()').extract()) 71 | except Exception as error: 72 | item['music_rating'] = '0' 73 | item['music_votes'] = '0' 74 | log(error) 75 | item['music_tags'] = "|".join(response.xpath('//*[@id="db-tags-section"]/div/a/text()').extract()) 76 | item['music_url'] = response.url 77 | yield item 78 | except Exception as error: 79 | log(error) 80 | 81 | def parse_review(self, response): 82 | try: 83 | item = MusicReviewItem() 84 | item['review_title'] = "".join(response.xpath('//*[@property="v:summary"]/text()').extract()) 85 | content = "".join( 86 | response.xpath('//*[@id="link-report"]/div[@property="v:description"]/text()').extract()) 87 | item['review_content'] = content.lstrip().rstrip().replace("\n", " ") 88 | item['review_author'] = "".join(response.xpath('//*[@property = "v:reviewer"]/text()').extract()) 89 | item['review_music'] = "".join(response.xpath('//*[@class="main-hd"]/a[2]/text()').extract()) 90 | item['review_time'] = "".join(response.xpath('//*[@class="main-hd"]/p/text()').extract()) 91 | item['review_url'] = response.url 92 | yield item 93 | except Exception as error: 94 | log(error) 95 | -------------------------------------------------------------------------------- /mysql/spiders/run.py: -------------------------------------------------------------------------------- 1 | # coding:utf-8 2 | 3 | 4 | from scrapy import cmdline 5 | 6 | cmdline.execute("scrapy crawl music".split()) 7 | cmdline.execute("scrapy crawl video".split()) 8 | -------------------------------------------------------------------------------- /mysql/spiders/videospider.py: -------------------------------------------------------------------------------- 1 | # coding:utf-8 2 | 3 | from scrapy.spider import CrawlSpider, Rule 4 | from scrapy.linkextractors import LinkExtractor 5 | from mysql.items import VideoItem, VideoReviewItem 6 | from scrapy import log 7 | 8 | import re 9 | 10 | AREA = re.compile(r"制片国家/地区: (.+?)
") 11 | ALIAS = re.compile(r"又名: (.+?)
") 12 | LANGUAGE = re.compile(r"语言: (.+?)
") 13 | EPISODES = re.compile(r"集数: (.+?)
") 14 | LENGTH = re.compile(r"单集片长: (.+?)
") 15 | 16 | 17 | class VideoSpider(CrawlSpider): 18 | name = 'video' 19 | allowed_domains = ['movie.douban.com'] 20 | start_urls = ['https://movie.douban.com/tag/', 21 | 'https://movie.douban.com/tag/?view=cloud' 22 | ] 23 | rules = (Rule(LinkExtractor(allow=r"/tag/((\d+)|([\u4e00-\u9fa5]+)|(\w+))$")), 24 | Rule(LinkExtractor(allow=r"/tag/((\d+)|([\u4e00-\u9fa5]+)|(\w+))\?start=\d+\&type=T$")), 25 | Rule(LinkExtractor(allow=r"/subject/\d+/reviews$")), 26 | Rule(LinkExtractor(allow=r"/subject/\d+/reviews\?start=\d+$")), 27 | Rule(LinkExtractor(allow=r"/subject/\d+/$"), callback="parse_video", follow=True), 28 | Rule(LinkExtractor(allow=r"/review/\d+/$"), callback="parse_review", follow=True), 29 | ) 30 | 31 | def parse_video(self, response): 32 | item = VideoItem() 33 | try: 34 | item["video_url"] = response.url 35 | item["video_name"] = ''.join( 36 | response.xpath('//*[@id="content"]/h1/span[@property="v:itemreviewed"]/text()').extract()) 37 | try: 38 | item["video_year"] = ''.join( 39 | response.xpath('//*[@id="content"]/h1/span[@class="year"]/text()').extract()).replace( 40 | "(", "").replace(")", "") 41 | except Exception as e: 42 | print('Exception:', e) 43 | item['video_year'] = '' 44 | 45 | introduction = response.xpath('//*[@id="link-report"]/span[@property="v:summary"]/text()').extract() 46 | if introduction: 47 | item["video_desc"] = ''.join(introduction).strip().replace("\r\n", " ") 48 | else: 49 | item["video_desc"] = ''.join( 50 | response.xpath('//*[@id="link-report"]/span/text()').extract()).strip().replace("\r\n", " ") 51 | 52 | item["video_director"] = "|".join( 53 | response.xpath('//*[@id="info"]/span/span/a[@rel="v:directedBy"]/text()').extract()) 54 | item["video_writer"] = "|".join( 55 | response.xpath('//*[@id="info"]/span[2]/span[2]/a/text()').extract()) 56 | 57 | item["video_actor"] = "|".join(response.xpath("//a[@rel='v:starring']/text()").extract()) 58 | 59 | item["video_type"] = "|".join(response.xpath('//*[@id="info"]/span[@property="v:genre"]/text()').extract()) 60 | 61 | S = "".join(response.xpath("//div[@id='info']").extract()) 62 | M = AREA.search(S) 63 | if M is not None: 64 | item["video_area"] = "|".join([area.strip() for area in M.group(1).split("/")]) 65 | else: 66 | item['video_area'] = '' 67 | 68 | A = "".join(response.xpath("//div[@id='info']").extract()) 69 | AL = ALIAS.search(A) 70 | if AL is not None: 71 | item["video_alias"] = "|".join([alias.strip() for alias in AL.group(1).split("/")]) 72 | else: 73 | item["video_alias"] = "" 74 | 75 | video_info = "".join(response.xpath("//div[@id='info']").extract()) 76 | language = LANGUAGE.search(video_info) 77 | episodes = EPISODES.search(video_info) 78 | length = LENGTH.search(video_info) 79 | 80 | if language is not None: 81 | item["video_language"] = "|".join([language.strip() for language in language.group(1).split("/")]) 82 | else: 83 | item['video_language'] = '' 84 | if length is not None: 85 | item["video_length"] = "|".join([runtime.strip() for runtime in length.group(1).split("/")]) 86 | else: 87 | item["video_length"] = "".join( 88 | response.xpath('//*[@id="info"]/span[@property="v:runtime"]/text()').extract()) 89 | 90 | item['video_time'] = "/".join( 91 | response.xpath('//*[@id="info"]/span[@property="v:initialReleaseDate"]/text()').extract()) 92 | if episodes is not None: 93 | item['video_bigtype'] = "电视剧" 94 | item["video_episodes"] = "|".join([episodes.strip() for episodes in episodes.group(1).split("/")]) 95 | else: 96 | item['video_bigtype'] = "电影" 97 | item['video_episodes'] = '' 98 | item['video_tags'] = "|".join( 99 | response.xpath('//*[@class="tags"]/div[@class="tags-body"]/a/text()').extract()) 100 | 101 | try: 102 | item['video_rating'] = "".join(response.xpath( 103 | '//*[@class="rating_self clearfix"]/strong/text()').extract()) 104 | item['video_votes'] = "".join(response.xpath( 105 | '//*[@class="rating_self clearfix"]/div/div[@class="rating_sum"]/a/span/text()').extract()) 106 | except Exception as error: 107 | item['video_rating'] = '0' 108 | item['video_votes'] = '0' 109 | log(error) 110 | 111 | yield item 112 | except Exception as error: 113 | log(error) 114 | 115 | def parse_review(self, response): 116 | try: 117 | item = VideoReviewItem() 118 | item['review_title'] = "".join(response.xpath('//*[@property="v:summary"]/text()').extract()) 119 | content = "".join( 120 | response.xpath('//*[@id="link-report"]/div[@property="v:description"]/text()').extract()) 121 | item['review_content'] = content.lstrip().rstrip().replace("\n", " ") 122 | item['review_author'] = "".join(response.xpath('//*[@property = "v:reviewer"]/text()').extract()) 123 | item['review_video'] = "".join(response.xpath('//*[@class="main-hd"]/a[2]/text()').extract()) 124 | item['review_time'] = "".join(response.xpath('//*[@class="main-hd"]/p/text()').extract()) 125 | item['review_url'] = response.url 126 | yield item 127 | except Exception as error: 128 | log(error) 129 | -------------------------------------------------------------------------------- /scrapy.cfg: -------------------------------------------------------------------------------- 1 | # Automatically created by: scrapy startproject 2 | # 3 | # For more information about the [deploy] section see: 4 | # https://scrapyd.readthedocs.org/en/latest/deploy.html 5 | 6 | [settings] 7 | default = mysql.settings 8 | 9 | [deploy] 10 | #url = http://localhost:6800/ 11 | project = mysql 12 | --------------------------------------------------------------------------------