├── LICENSE.txt ├── README.md ├── redisstorage.go └── redisstorage_test.go /LICENSE.txt: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Redis Storage for Colly 2 | 3 | This is a redis based storage backend for [Colly](https://github.com/gocolly/colly) collectors. 4 | 5 | [![GoDoc](https://godoc.org/github.com/gocolly/redisstorage?status.svg)](https://godoc.org/github.com/gocolly/redisstorage) 6 | 7 | ## Install 8 | 9 | ``` 10 | go get -u github.com/gocolly/redisstorage 11 | ``` 12 | 13 | 14 | ## Usage 15 | 16 | ```go 17 | import ( 18 | "github.com/gocolly/colly" 19 | "github.com/gocolly/redisstorage" 20 | ) 21 | ``` 22 | 23 | 24 | ```go 25 | c := colly.NewCollector() 26 | 27 | storage := &redisstorage.Storage{ 28 | Address: "127.0.0.1:6379", 29 | Password: "", 30 | DB: 0, 31 | Prefix: "job01", 32 | } 33 | 34 | err := c.SetStorage(storage) 35 | if err != nil { 36 | panic(err) 37 | } 38 | ``` 39 | 40 | 41 | ## Bugs 42 | 43 | Bugs or suggestions? Visit the [issue tracker](https://github.com/gocolly/redisstorage/issues) or join `#colly` on freenode 44 | -------------------------------------------------------------------------------- /redisstorage.go: -------------------------------------------------------------------------------- 1 | package redisstorage 2 | 3 | import ( 4 | "fmt" 5 | "log" 6 | "net/url" 7 | "sync" 8 | "time" 9 | 10 | "github.com/go-redis/redis" 11 | ) 12 | 13 | // Storage implements the redis storage backend for Colly 14 | type Storage struct { 15 | // Address is the redis server address 16 | Address string 17 | // Password is the password for the redis server 18 | Password string 19 | // DB is the redis database. Default is 0 20 | DB int 21 | // Prefix is an optional string in the keys. It can be used 22 | // to use one redis database for independent scraping tasks. 23 | Prefix string 24 | // Client is the redis connection 25 | Client *redis.Client 26 | 27 | // Expiration time for Visited keys. After expiration pages 28 | // are to be visited again. 29 | Expires time.Duration 30 | 31 | mu sync.RWMutex // Only used for cookie methods. 32 | } 33 | 34 | // Init initializes the redis storage 35 | func (s *Storage) Init() error { 36 | if s.Client == nil { 37 | s.Client = redis.NewClient(&redis.Options{ 38 | Addr: s.Address, 39 | Password: s.Password, 40 | DB: s.DB, 41 | }) 42 | } 43 | _, err := s.Client.Ping().Result() 44 | if err != nil { 45 | return fmt.Errorf("Redis connection error: %s", err.Error()) 46 | } 47 | return err 48 | } 49 | 50 | // Clear removes all entries from the storage 51 | func (s *Storage) Clear() error { 52 | s.mu.Lock() 53 | defer s.mu.Unlock() 54 | r := s.Client.Keys(s.getCookieID("*")) 55 | keys, err := r.Result() 56 | if err != nil { 57 | return err 58 | } 59 | r2 := s.Client.Keys(s.Prefix + ":request:*") 60 | keys2, err := r2.Result() 61 | if err != nil { 62 | return err 63 | } 64 | keys = append(keys, keys2...) 65 | keys = append(keys, s.getQueueID()) 66 | return s.Client.Del(keys...).Err() 67 | } 68 | 69 | // Visited implements colly/storage.Visited() 70 | func (s *Storage) Visited(requestID uint64) error { 71 | return s.Client.Set(s.getIDStr(requestID), "1", s.Expires).Err() 72 | } 73 | 74 | // IsVisited implements colly/storage.IsVisited() 75 | func (s *Storage) IsVisited(requestID uint64) (bool, error) { 76 | _, err := s.Client.Get(s.getIDStr(requestID)).Result() 77 | if err == redis.Nil { 78 | return false, nil 79 | } else if err != nil { 80 | return false, err 81 | } 82 | return true, nil 83 | } 84 | 85 | // SetCookies implements colly/storage..SetCookies() 86 | func (s *Storage) SetCookies(u *url.URL, cookies string) { 87 | // TODO(js) Cookie methods currently have no way to return an error. 88 | 89 | // We need to use a write lock to prevent a race in the db: 90 | // if two callers set cookies in a very small window of time, 91 | // it is possible to drop the new cookies from one caller 92 | // ('last update wins' == best avoided). 93 | s.mu.Lock() 94 | defer s.mu.Unlock() 95 | // return s.Client.Set(s.getCookieID(u.Host), stringify(cnew), 0).Err() 96 | err := s.Client.Set(s.getCookieID(u.Host), cookies, 0).Err() 97 | if err != nil { 98 | // return nil 99 | log.Printf("SetCookies() .Set error %s", err) 100 | return 101 | } 102 | } 103 | 104 | // Cookies implements colly/storage.Cookies() 105 | func (s *Storage) Cookies(u *url.URL) string { 106 | // TODO(js) Cookie methods currently have no way to return an error. 107 | 108 | s.mu.RLock() 109 | cookiesStr, err := s.Client.Get(s.getCookieID(u.Host)).Result() 110 | s.mu.RUnlock() 111 | if err == redis.Nil { 112 | cookiesStr = "" 113 | } else if err != nil { 114 | // return nil, err 115 | log.Printf("Cookies() .Get error %s", err) 116 | return "" 117 | } 118 | return cookiesStr 119 | } 120 | 121 | // AddRequest implements queue.Storage.AddRequest() function 122 | func (s *Storage) AddRequest(r []byte) error { 123 | return s.Client.RPush(s.getQueueID(), r).Err() 124 | } 125 | 126 | // GetRequest implements queue.Storage.GetRequest() function 127 | func (s *Storage) GetRequest() ([]byte, error) { 128 | r, err := s.Client.LPop(s.getQueueID()).Bytes() 129 | if err != nil { 130 | return nil, err 131 | } 132 | return r, err 133 | } 134 | 135 | // QueueSize implements queue.Storage.QueueSize() function 136 | func (s *Storage) QueueSize() (int, error) { 137 | i, err := s.Client.LLen(s.getQueueID()).Result() 138 | return int(i), err 139 | } 140 | 141 | func (s *Storage) getIDStr(ID uint64) string { 142 | return fmt.Sprintf("%s:request:%d", s.Prefix, ID) 143 | } 144 | 145 | func (s *Storage) getCookieID(c string) string { 146 | return fmt.Sprintf("%s:cookie:%s", s.Prefix, c) 147 | } 148 | 149 | func (s *Storage) getQueueID() string { 150 | return fmt.Sprintf("%s:queue", s.Prefix) 151 | } 152 | -------------------------------------------------------------------------------- /redisstorage_test.go: -------------------------------------------------------------------------------- 1 | package redisstorage 2 | 3 | import ( 4 | "testing" 5 | ) 6 | 7 | func TestQueue(t *testing.T) { 8 | s := &Storage{ 9 | Address: "127.0.0.1:6379", 10 | Password: "", 11 | DB: 0, 12 | Prefix: "queue_test", 13 | } 14 | 15 | if err := s.Init(); err != nil { 16 | t.Error("failed to initialize client: " + err.Error()) 17 | return 18 | } 19 | defer s.Clear() 20 | urls := []string{"http://example.com/", "http://go-colly.org/", "https://xx.yy/zz"} 21 | for _, u := range urls { 22 | if err := s.AddRequest([]byte(u)); err != nil { 23 | t.Error("failed to add request: " + err.Error()) 24 | return 25 | } 26 | } 27 | if size, err := s.QueueSize(); size != 3 || err != nil { 28 | t.Error("invalid queue size") 29 | return 30 | } 31 | for _, u := range urls { 32 | if r, err := s.GetRequest(); err != nil || string(r) != u { 33 | t.Error("failed to get request: " + err.Error()) 34 | return 35 | } 36 | } 37 | } 38 | --------------------------------------------------------------------------------