├── .gitignore ├── LICENSE ├── README.md ├── scrapy.cfg └── scrapyspider ├── __init__.py ├── items.py ├── pipelines.py ├── run.py ├── settings.py └── spiders ├── __init__.py ├── blog_spider.py ├── douban_ajax_spider.py └── douban_spider.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | .Ds_Store 3 | 4 | -------------------------------------------------------------------------------- /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 | # scrapy-tutorial 2 | Scrapy 爬虫框架教程源码 3 | 1. [scrapy爬虫框架教程（一）-- Scrapy入门](https://woodenrobot.me/2017/01/01/scrapy%E7%88%AC%E8%99%AB%E6%A1%86%E6%9E%B6%E6%95%99%E7%A8%8B%EF%BC%88%E4%B8%80%EF%BC%89-Scrapy%E5%85%A5%E9%97%A8/) 4 | 2. [Scrapy爬虫框架教程（二）-- 爬取豆瓣电影TOP250](https://woodenrobot.me/2017/01/07/Scrapy%E7%88%AC%E8%99%AB%E6%A1%86%E6%9E%B6%E6%95%99%E7%A8%8B%EF%BC%88%E4%BA%8C%EF%BC%89-%E7%88%AC%E5%8F%96%E8%B1%86%E7%93%A3%E7%94%B5%E5%BD%B1TOP250/) 5 | 3. [Scrapy爬虫框架教程（三）-- 调试(Debugging)Spiders](https://woodenrobot.me/2017/02/12/Scrapy%E7%88%AC%E8%99%AB%E6%A1%86%E6%9E%B6%E6%95%99%E7%A8%8B%EF%BC%88%E4%B8%89%EF%BC%89-%E8%B0%83%E8%AF%95-Debugging-Spiders/) 6 | 4. [Scrapy爬虫框架教程（四）-- 抓取AJAX异步加载网页](https://woodenrobot.me/2017/04/09/Scrapy%E7%88%AC%E8%99%AB%E6%A1%86%E6%9E%B6%E6%95%99%E7%A8%8B%EF%BC%88%E5%9B%9B%EF%BC%89-%E6%8A%93%E5%8F%96AJAX%E5%BC%82%E6%AD%A5%E5%8A%A0%E8%BD%BD%E7%BD%91%E9%A1%B5/) 7 | -------------------------------------------------------------------------------- /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 = scrapyspider.settings 8 | 9 | [deploy] 10 | #url = http://localhost:6800/ 11 | project = scrapyspider 12 | -------------------------------------------------------------------------------- /scrapyspider/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Wooden-Robot/scrapy-tutorial/3f96f41c0cadf7a3504810ff10372a977f45ab3c/scrapyspider/__init__.py -------------------------------------------------------------------------------- /scrapyspider/items.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Define here the models for your scraped items 4 | # 5 | # See documentation in: 6 | # http://doc.scrapy.org/en/latest/topics/items.html 7 | 8 | import scrapy 9 | 10 | 11 | class DoubanMovieItem(scrapy.Item): 12 | # 排名 13 | ranking = scrapy.Field() 14 | # 电影名称 15 | movie_name = scrapy.Field() 16 | # 评分 17 | score = scrapy.Field() 18 | # 评论人数 19 | score_num = scrapy.Field() -------------------------------------------------------------------------------- /scrapyspider/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 | 8 | 9 | class ScrapyspiderPipeline(object): 10 | def process_item(self, item, spider): 11 | return item 12 | -------------------------------------------------------------------------------- /scrapyspider/run.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Time : 2017/1/1 17:51 3 | # @Author : woodenrobot 4 | 5 | 6 | from scrapy import cmdline 7 | 8 | 9 | name = 'douban_movie_top250' 10 | cmd = 'scrapy crawl {0}'.format(name) 11 | cmdline.execute(cmd.split()) -------------------------------------------------------------------------------- /scrapyspider/settings.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Scrapy settings for scrapyspider 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 = 'scrapyspider' 13 | 14 | SPIDER_MODULES = ['scrapyspider.spiders'] 15 | NEWSPIDER_MODULE = 'scrapyspider.spiders' 16 | 17 | 18 | # Crawl responsibly by identifying yourself (and your website) on the user-agent 19 | #USER_AGENT = 'scrapyspider (+http://www.yourdomain.com)' 20 | 21 | # Obey robots.txt rules 22 | ROBOTSTXT_OBEY = False 23 | 24 | # Configure maximum concurrent requests performed by Scrapy (default: 16) 25 | #CONCURRENT_REQUESTS = 32 26 | 27 | # Configure a delay for requests for the same website (default: 0) 28 | # See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay 29 | # See also autothrottle settings and docs 30 | #DOWNLOAD_DELAY = 3 31 | # The download delay setting will honor only one of: 32 | #CONCURRENT_REQUESTS_PER_DOMAIN = 16 33 | #CONCURRENT_REQUESTS_PER_IP = 16 34 | 35 | # Disable cookies (enabled by default) 36 | #COOKIES_ENABLED = False 37 | 38 | # Disable Telnet Console (enabled by default) 39 | #TELNETCONSOLE_ENABLED = False 40 | 41 | # Override the default request headers: 42 | #DEFAULT_REQUEST_HEADERS = { 43 | # 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8', 44 | # 'Accept-Language': 'en', 45 | #} 46 | 47 | # Enable or disable spider middlewares 48 | # See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html 49 | #SPIDER_MIDDLEWARES = { 50 | # 'scrapyspider.middlewares.MyCustomSpiderMiddleware': 543, 51 | #} 52 | 53 | # Enable or disable downloader middlewares 54 | # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html 55 | #DOWNLOADER_MIDDLEWARES = { 56 | # 'scrapyspider.middlewares.MyCustomDownloaderMiddleware': 543, 57 | #} 58 | 59 | # Enable or disable extensions 60 | # See http://scrapy.readthedocs.org/en/latest/topics/extensions.html 61 | #EXTENSIONS = { 62 | # 'scrapy.extensions.telnet.TelnetConsole': None, 63 | #} 64 | 65 | # Configure item pipelines 66 | # See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html 67 | #ITEM_PIPELINES = { 68 | # 'scrapyspider.pipelines.SomePipeline': 300, 69 | #} 70 | 71 | # Enable and configure the AutoThrottle extension (disabled by default) 72 | # See http://doc.scrapy.org/en/latest/topics/autothrottle.html 73 | #AUTOTHROTTLE_ENABLED = True 74 | # The initial download delay 75 | #AUTOTHROTTLE_START_DELAY = 5 76 | # The maximum download delay to be set in case of high latencies 77 | #AUTOTHROTTLE_MAX_DELAY = 60 78 | # The average number of requests Scrapy should be sending in parallel to 79 | # each remote server 80 | #AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0 81 | # Enable showing throttling stats for every response received: 82 | #AUTOTHROTTLE_DEBUG = False 83 | 84 | # Enable and configure HTTP caching (disabled by default) 85 | # See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings 86 | #HTTPCACHE_ENABLED = True 87 | #HTTPCACHE_EXPIRATION_SECS = 0 88 | #HTTPCACHE_DIR = 'httpcache' 89 | #HTTPCACHE_IGNORE_HTTP_CODES = [] 90 | #HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage' 91 | -------------------------------------------------------------------------------- /scrapyspider/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 | -------------------------------------------------------------------------------- /scrapyspider/spiders/blog_spider.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Time : 2017/1/1 17:34 3 | # @Author : woodenrobot 4 | 5 | 6 | from scrapy.spiders import Spider 7 | 8 | 9 | class BlogSpider(Spider): 10 | name = 'woodenrobot' 11 | start_urls = ['https://woodenrobot.me'] 12 | 13 | def parse(self, response): 14 | titles = response.xpath('//a[@class="post-title-link"]/text()').extract() 15 | for title in titles: 16 | print title.strip() 17 | -------------------------------------------------------------------------------- /scrapyspider/spiders/douban_ajax_spider.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Time : 2017/4/9 14:32 3 | # @Author : woodenrobot 4 | 5 | 6 | import re 7 | import json 8 | 9 | 10 | from scrapy import Request 11 | from scrapy.spiders import Spider 12 | from scrapyspider.items import DoubanMovieItem 13 | 14 | 15 | class DoubanAJAXSpider(Spider): 16 | name = 'douban_ajax' 17 | headers = { 18 | 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36', 19 | } 20 | 21 | def start_requests(self): 22 | url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start=0&limit=20' 23 | yield Request(url, headers=self.headers) 24 | 25 | def parse(self, response): 26 | datas = json.loads(response.body) 27 | item = DoubanMovieItem() 28 | if datas: 29 | for data in datas: 30 | item['ranking'] = data['rank'] 31 | item['movie_name'] = data['title'] 32 | item['score'] = data['score'] 33 | item['score_num'] = data['vote_count'] 34 | yield item 35 | 36 | # 如果datas存在数据则对下一页进行采集 37 | page_num = re.search(r'start=(\d+)', response.url).group(1) 38 | page_num = 'start=' + str(int(page_num)+20) 39 | next_url = re.sub(r'start=\d+', page_num, response.url) 40 | yield Request(next_url, headers=self.headers) -------------------------------------------------------------------------------- /scrapyspider/spiders/douban_spider.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # @Time : 2017/1/7 17:04 3 | # @Author : woodenrobot 4 | 5 | 6 | from scrapy import Request 7 | from scrapy.spiders import Spider 8 | from scrapyspider.items import DoubanMovieItem 9 | 10 | 11 | class DoubanMovieTop250Spider(Spider): 12 | name = 'douban_movie_top250' 13 | headers = { 14 | 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36', 15 | } 16 | 17 | def start_requests(self): 18 | url = 'https://movie.douban.com/top250' 19 | yield Request(url, headers=self.headers) 20 | 21 | def parse(self, response): 22 | item = DoubanMovieItem() 23 | movies = response.xpath('//ol[@class="grid_view"]/li') 24 | for movie in movies: 25 | item['ranking'] = movie.xpath( 26 | './/div[@class="pic"]/em/text()').extract()[0] 27 | item['movie_name'] = movie.xpath( 28 | './/div[@class="hd"]/a/span[1]/text()').extract()[0] 29 | item['score'] = movie.xpath( 30 | './/div[@class="star"]/span[@class="rating_num"]/text()' 31 | ).extract()[0] 32 | item['score_num'] = movie.xpath( 33 | './/div[@class="star"]/span/text()').re(ur'(\d+)人评价')[0] 34 | yield item 35 | 36 | next_url = response.xpath('//span[@class="next"]/a/@href').extract() 37 | if next_url: 38 | next_url = 'https://movie.douban.com/top250' + next_url[0] 39 | yield Request(next_url, headers=self.headers) --------------------------------------------------------------------------------