├── art └── 1.png ├── win_exe └── main.zip ├── code ├── rule │ ├── ruleProvider.go │ ├── rule.go │ ├── meirule.go │ └── jandanRule.go ├── main.go └── meizar │ └── meizar.go ├── .gitignore ├── README.md └── LICENSE /art/1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qibin0506/Meizar/HEAD/art/1.png -------------------------------------------------------------------------------- /win_exe/main.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/qibin0506/Meizar/HEAD/win_exe/main.zip -------------------------------------------------------------------------------- /code/rule/ruleProvider.go: -------------------------------------------------------------------------------- 1 | package rule 2 | 3 | func RuleProvider() Rule { 4 | return &JandanRule{} 5 | } 6 | -------------------------------------------------------------------------------- /code/rule/rule.go: -------------------------------------------------------------------------------- 1 | package rule 2 | 3 | import ( 4 | "github.com/PuerkitoBio/goquery" 5 | ) 6 | 7 | type Rule interface { 8 | UrlRule() (url string) 9 | PageRule(currentPage int) (page string) 10 | ImageRule(doc *goquery.Document, f func(image string)) 11 | } 12 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Compiled Object files, Static and Dynamic libs (Shared Objects) 2 | *.o 3 | *.a 4 | *.so 5 | 6 | # Folders 7 | _obj 8 | _test 9 | 10 | # Architecture specific extensions/prefixes 11 | *.[568vq] 12 | [568vq].out 13 | 14 | *.cgo1.go 15 | *.cgo2.c 16 | _cgo_defun.c 17 | _cgo_gotypes.go 18 | _cgo_export.* 19 | 20 | _testmain.go 21 | 22 | *.exe 23 | *.test 24 | *.prof 25 | -------------------------------------------------------------------------------- /code/rule/meirule.go: -------------------------------------------------------------------------------- 1 | package rule 2 | 3 | import ( 4 | "github.com/PuerkitoBio/goquery" 5 | "strconv" 6 | ) 7 | 8 | type MeiRule struct{} 9 | 10 | func (p *MeiRule) UrlRule() string { 11 | return "https://meizi.us/" 12 | } 13 | 14 | func (p *MeiRule) PageRule(currentPage int) (page string) { 15 | return "?page=" + strconv.Itoa(currentPage) 16 | } 17 | 18 | func (p *MeiRule) ImageRule(doc *goquery.Document, f func(image string)) { 19 | doc.Find("img.img-responsive").Each(func(i int, s *goquery.Selection) { 20 | if img, exist := s.Attr("src"); exist { 21 | f(img) 22 | } 23 | }) 24 | } 25 | -------------------------------------------------------------------------------- /code/main.go: -------------------------------------------------------------------------------- 1 | package main 2 | 3 | import ( 4 | "./meizar" 5 | "./rule" 6 | "flag" 7 | "net/http" 8 | "runtime" 9 | "strings" 10 | ) 11 | 12 | var dir *string = flag.String("dir", "./images/", "") 13 | var startPage *int = flag.Int("start", 2009, "") 14 | var userCookie *string = flag.String("cookie", "1092990552=903f5Z2FA411DxfPYORhRDmNqohZzkNsnLuvj76u; PHPSESSID=vq5be8aobr23gdt68ig0mmud31; 1092990552=0; _gat=1; jdna=596e6fb28c1bb47f949e65e1ae03f7f5#1465139210979; Hm_lvt_fd93b7fb546adcfbcf80c4fc2b54da2c=1465130953,1465137904; Hm_lpvt_fd93b7fb546adcfbcf80c4fc2b54da2c=1465139211; _ga=GA1.2.1645811469.1465130953", "") 15 | var pageSort *int = flag.Int("pagesort", 0, "") 16 | var client *http.Client = &http.Client{} 17 | 18 | func init() { 19 | flag.Parse() 20 | if !strings.HasSuffix(*dir, "/") { 21 | *dir = *dir + "/" 22 | } 23 | } 24 | 25 | func main() { 26 | runtime.GOMAXPROCS(runtime.NumCPU()) 27 | meizar.New(*dir, *startPage, rule.RuleProvider(), *userCookie, client, *pageSort).Start() 28 | } 29 | -------------------------------------------------------------------------------- /code/rule/jandanRule.go: -------------------------------------------------------------------------------- 1 | package rule 2 | 3 | import ( 4 | // "fmt" 5 | "github.com/PuerkitoBio/goquery" 6 | // "github.com/robertkrimen/otto" 7 | "encoding/base64" 8 | "strconv" 9 | ) 10 | 11 | type JandanRule struct{} 12 | 13 | func (p *JandanRule) UrlRule() (url string) { 14 | return "http://jandan.net/ooxx/" 15 | } 16 | 17 | func (p *JandanRule) PageRule(currentPage int) (page string) { 18 | return "page-" + strconv.Itoa(currentPage) 19 | } 20 | 21 | func (p *JandanRule) ImageRule(doc *goquery.Document, f func(image string)) { 22 | // doc.Find("a.view_img_link").Each(func(i int, s *goquery.Selection) { 23 | // if img, exist := s.Attr("href"); exist { 24 | // f(img) 25 | // } 26 | // }) 27 | 28 | doc.Find("span.img-hash").Each(func(i int, s *goquery.Selection) { 29 | hash_value := s.Text() 30 | decoded, err := base64.StdEncoding.DecodeString(hash_value) 31 | if err == nil { 32 | img := "http:" + string(decoded) 33 | // fmt.Println(hash_value + "->" + img) 34 | f(img) 35 | } 36 | }) 37 | } 38 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Meizar（注意：仅供娱乐） 2 | 3 | golang实现抓取妹子图 4 | 5 | 默认图片来源网站：[http://jandan.net](http://jandan.net) 6 | 7 | 依赖项目：[https://github.com/PuerkitoBio/goquery](https://github.com/PuerkitoBio/goquery) 8 | 9 | ## 2016/6/7更新 10 | 11 | 1. 增加RuleProvider函数，所以，切换Rule时，只需要修改RuleProvider的返回值就可以 12 | 2. 增加一个新的Rule-MeiRule，该Rule用来抓取[https://meizi.us/](https://meizi.us/)图片 13 | 3. 增加pagesort参数，用来指定页码增加规则， 1为升序，0为降序，默认为0 14 | 15 | 默认的Rule还是JandanRule， 想要切换到MeiRule的方法是： 16 | 修改/rule/ruleProvider.go文件，将RuleProvider方法的返回值指定为MeiRule. 17 | 代码： 18 | 19 | ``` go 20 | func RuleProvider() Rule { 21 | return &MeiRule{} 22 | } 23 | ``` 24 | 25 | ## 如何使用 26 | 27 | window用户可以直接下载**win_exe**目录下在的zip文件，解压出一个main.exe文件。 28 | 29 | 其他平台用户，可以自行下载源码编译。 30 | 31 | 使用步骤(以windows为例)： 32 | 33 | 1. 打开命令行定位到编译文件所在目录 34 | 2. 输入命令： 35 | 36 | > main.exe -dir D:\jandan -start 2009 37 | 38 | ## 参数说明 39 | 40 | 1. -dir 可选， 制定图片保存路径，默认保存当前目录/images/下 41 | 2. -start 可选，从多少页开始，默认从第2009页开始抓取(注意程序是按照页码倒序抓取的) 42 | 3. -cookie 可选，用户使用的cookie， chrome下可以打开[http://jandan.net](http://jandan.net)，按F12键，选择network项查看，这个参数主要在抓取时发生503错误使用的，默认不用指定 43 | 4. -pagesort 可选，指定页码增加规则， 1为升序，0为降序，默认为0 44 | 45 | ## 效果 46 | 47 | ![](./art/1.png) 48 | 49 | ^_^ 图片就不展示了， 大家可以自己运行看。 50 | 51 | ## 扩展 52 | 53 | 默认图片来源是[煎蛋](http://jandan.net)上的， 但是作为一个___，难道一个煎蛋就满足了吗？不可能！！！！ 54 | 所以，我们还可以自定义抓取规则，来抓取不同网站的内容。 55 | 56 | 怎么定制？ 57 | 58 | 只需要实现`Rule`接口的3个方法就可以了。例如煎蛋的抓取规则是： 59 | ``` go 60 | // /rule/jandanRule.go 61 | type JandanRule struct{} 62 | 63 | func (p *JandanRule) UrlRule() (url string) { 64 | return "http://jandan.net/ooxx/" 65 | } 66 | 67 | func (p *JandanRule) PageRule(currentPage int) (page string) { 68 | return "page-" + strconv.Itoa(currentPage) 69 | } 70 | 71 | func (p *JandanRule) ImageRule(doc *goquery.Document, f func(image string)) { 72 | doc.Find("a.view_img_link").Each(func(i int, s *goquery.Selection) { 73 | if img, exist := s.Attr("href"); exist { 74 | f(img) 75 | } 76 | }) 77 | } 78 | ``` 79 | 1. 第一个方法返回我们要抓取的url 80 | 2. 第二个方法根据当前页返回url后面的页面信息 81 | 3. 第三个方法是内容匹配规则， 将匹配到的内容利用f函数返回 82 | 83 | 还有哪些你喜欢的网站呢？ 赶紧定制规则来尝试抓取吧。 或者提Issue我来添加抓取规则！ 84 | -------------------------------------------------------------------------------- /code/meizar/meizar.go: -------------------------------------------------------------------------------- 1 | package meizar 2 | 3 | import ( 4 | "../rule" 5 | "bytes" 6 | "fmt" 7 | "github.com/PuerkitoBio/goquery" 8 | // "github.com/rs/xid" 9 | "io" 10 | "io/ioutil" 11 | "net/http" 12 | "os" 13 | // "path/filepath" 14 | "strconv" 15 | "strings" 16 | "time" 17 | ) 18 | 19 | func New(dir string, startPage int, r rule.Rule, cookie string, client *http.Client, pageSort int) *Meizar { 20 | return &Meizar{dir: dir, currentPage: startPage, userCookie: cookie, r: r, client: client, pageSort: pageSort} 21 | } 22 | 23 | type Meizar struct { 24 | dir string 25 | currentPage int 26 | userCookie string 27 | client *http.Client 28 | r rule.Rule 29 | pageSort int 30 | } 31 | 32 | func (p *Meizar) Start() { 33 | if !p.isExist(p.dir) { 34 | if err := os.Mkdir(p.dir, 0777); err != nil { 35 | panic("can not mkdir " + p.dir) 36 | } 37 | } 38 | 39 | for p.currentPage > 0 { 40 | time.Sleep(1e9) 41 | p.parsePage(p.r.UrlRule() + p.r.PageRule(p.currentPage)) 42 | if p.pageSort == 1 { 43 | p.currentPage++ 44 | } else { 45 | p.currentPage-- 46 | } 47 | } 48 | } 49 | 50 | func (p *Meizar) parsePage(url string) { 51 | req := p.buildRequest(url) 52 | resp, err := p.client.Do(req) 53 | 54 | if err != nil { 55 | fmt.Println("failed parse " + url) 56 | return 57 | } 58 | 59 | if resp.StatusCode != http.StatusOK { 60 | fmt.Println(url + "-->" + strconv.Itoa(resp.StatusCode)) 61 | return 62 | } 63 | 64 | defer resp.Body.Close() 65 | 66 | data, _ := ioutil.ReadAll(resp.Body) 67 | img, err := p.parseImageUrl(bytes.NewReader(data)) 68 | if err != nil { 69 | fmt.Println(err) 70 | return 71 | } 72 | 73 | for _, item := range img { 74 | go p.downloadImage(item) 75 | } 76 | } 77 | 78 | func (p *Meizar) buildRequest(url string) *http.Request { 79 | req, err := http.NewRequest("GET", url, nil) 80 | if err != nil { 81 | panic(err) 82 | } 83 | 84 | req.Header.Set("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.152 Safari/537.36") 85 | req.Header.Set("Cookie", p.userCookie) 86 | return req 87 | } 88 | 89 | func (p *Meizar) parseImageUrl(reader io.Reader) (res []string, err error) { 90 | doc, err := goquery.NewDocumentFromReader(reader) 91 | if err != nil { 92 | return nil, err 93 | } 94 | 95 | p.r.ImageRule(doc, func(image string) { 96 | res = append(res, image) 97 | }) 98 | 99 | return res, nil 100 | } 101 | 102 | func (p *Meizar) downloadImage(url string) { 103 | fileName := p.getNameFromUrl(url) 104 | // guid := xid.New() 105 | // fileName := guid.String() + filepath.Ext(p.getNameFromUrl(url)) 106 | fmt.Println(url + "->" + fileName) 107 | if p.isExist(p.dir + fileName) { 108 | fmt.Println("already download " + fileName) 109 | return 110 | } 111 | 112 | req := p.buildRequest(url) 113 | resp, err := p.client.Do(req) 114 | if err != nil { 115 | fmt.Println("failed download " + url) 116 | } 117 | 118 | if resp.StatusCode != http.StatusOK { 119 | fmt.Println("failed download " + url) 120 | return 121 | } 122 | 123 | defer func() { 124 | resp.Body.Close() 125 | if r := recover(); r != nil { 126 | fmt.Println(r) 127 | } 128 | }() 129 | 130 | fmt.Println("begin download " + fileName) 131 | localFile, _ := os.OpenFile(p.dir+fileName, os.O_CREATE|os.O_RDWR, 0777) 132 | if _, err := io.Copy(localFile, resp.Body); err != nil { 133 | panic("failed save " + fileName) 134 | } 135 | 136 | fmt.Println("success download " + fileName) 137 | } 138 | 139 | func (p *Meizar) isExist(dir string) bool { 140 | _, err := os.Stat(dir) 141 | if err == nil { 142 | return true 143 | } 144 | 145 | return os.IsExist(err) 146 | } 147 | 148 | func (p *Meizar) getNameFromUrl(url string) string { 149 | arr := strings.Split(url, "/") 150 | return arr[len(arr)-1] 151 | } 152 | -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------