From 976137eea86afecddd6987ac3d2704110ff0260b Mon Sep 17 00:00:00 2001 From: tiennm99 Date: Sun, 21 Dec 2025 10:16:18 +0700 Subject: [PATCH] chore: migrate --- ghibli-gallery-crawler/download_images.js | 54 ++++ ghibli-gallery-crawler/download_images.py | 90 ++++++ ghibli-gallery-crawler/package-lock.json | 337 ++++++++++++++++++++++ 3 files changed, 481 insertions(+) create mode 100644 ghibli-gallery-crawler/download_images.js create mode 100644 ghibli-gallery-crawler/download_images.py create mode 100644 ghibli-gallery-crawler/package-lock.json diff --git a/ghibli-gallery-crawler/download_images.js b/ghibli-gallery-crawler/download_images.js new file mode 100644 index 0000000..cffab3f --- /dev/null +++ b/ghibli-gallery-crawler/download_images.js @@ -0,0 +1,54 @@ +const fs = require('fs') +const request = require('request') +const { + cookieCompare +} = require('tough-cookie') + +const download = (url, path, callback) => { + request.head(url, (err, res, body) => { + request(url) + .pipe(fs.createWriteStream(path)) + .on('close', callback) + }) +} + +// const url = 'https://…' +// const path = './images/image.png' + +// download(url, path, () => { +// console.log('✅ Done!') +// }) + +// let urlConst = "https://www.iamag.co/wp-content/uploads/2017/07/yourname-background" +// for (let i = 1; i < 200; i++) { +// download(urlConst + i + ".jpeg", "img/" + i + ".jpeg", () => { +// console.log("Done: " + i); +// }) +// } + +function lpad(n, width, z) { + z = z || '0'; + n = n + ''; + return n.length >= width ? n : new Array(width - n.length + 1).join(z) + n; +} + +let ghibli = "http://www.ghibli.jp/gallery/"; +let listFilm = ["marnie", "kaguyahime", "kazetachinu", "kokurikozaka", "karigurashi", "ponyo", "ged", "chihiro"]; +listFilm.forEach(film => { + let filmDir = "./" + film; + fs.mkdir(filmDir, function(err) { + if (err) { + console.log(err); + } else { + console.log("Created " + filmDir); + } + }); + for (let i = 1; i <= 50; i++) { + let imgName = lpad(i, 3) + ".jpg"; + let imgUrl = ghibli + film + imgName; + console.log(imgUrl); + download(imgUrl, filmDir + "/" + imgName, () => { + console.log("Done: " + imgName); + }) + } +}) \ No newline at end of file diff --git a/ghibli-gallery-crawler/download_images.py b/ghibli-gallery-crawler/download_images.py new file mode 100644 index 0000000..084069b --- /dev/null +++ b/ghibli-gallery-crawler/download_images.py @@ -0,0 +1,90 @@ +import requests +import os +from tqdm import tqdm +from bs4 import BeautifulSoup as bs +from urllib.parse import urljoin, urlparse + + +def is_valid(url): + """ + Checks whether `url` is a valid URL. + """ + parsed = urlparse(url) + return bool(parsed.netloc) and bool(parsed.scheme) + + +def get_all_images(url): + """ + Returns all image URLs on a single `url` + """ + soup = bs(requests.get(url).content, "html.parser") + urls = [] + for img in tqdm(soup.find_all("img"), "Extracting images"): + img_url = img.attrs.get("src") + if not img_url: + # if img does not contain src attribute, just skip + continue + # make the URL absolute by joining domain with the URL that is just extracted + img_url = urljoin(url, img_url) + # remove URLs like '/hsts-pixel.gif?c=3.2.5' + try: + pos = img_url.index("?") + img_url = img_url[:pos] + except ValueError: + pass + # finally, if the url is valid + if is_valid(img_url): + urls.append(img_url) + return urls + + +def download(url, pathname): + """ + Downloads a file given an URL and puts it in the folder `pathname` + """ + # if path doesn't exist, make that path dir + if not os.path.isdir(pathname): + os.makedirs(pathname) + # download the body of response by chunk, not immediately + response = requests.get(url, stream=True) + + # get the total file size + file_size = int(response.headers.get("Content-Length", 0)) + + # get the file name + filename = os.path.join(pathname, url.split("/")[-1]) + + # progress bar, changing the unit to bytes instead of iteration (default by tqdm) + progress = tqdm(response.iter_content(1024), f"Downloading {filename}", total=file_size, unit="B", unit_scale=True, unit_divisor=1024) + with open(filename, "wb") as f: + for data in progress: + # write data read to the file + f.write(data) + # update the progress bar manually + progress.update(len(data)) + + +def main(url, path): + # get all images + imgs = get_all_images(url) + for img in imgs: + # for each img, download it + download(img, path) + + + +if __name__ == "__main__": + import argparse + parser = argparse.ArgumentParser(description="This script downloads all images from a web page") + parser.add_argument("url", help="The URL of the web page you want to download images") + parser.add_argument("-p", "--path", help="The Directory you want to store your images, default is the domain of URL passed") + + args = parser.parse_args() + url = args.url + path = args.path + + if not path: + # if path isn't specified, use the domain name of that url as the folder name + path = urlparse(url).netloc + + main(url, path) \ No newline at end of file diff --git a/ghibli-gallery-crawler/package-lock.json b/ghibli-gallery-crawler/package-lock.json new file mode 100644 index 0000000..b8e2660 --- /dev/null +++ b/ghibli-gallery-crawler/package-lock.json @@ -0,0 +1,337 @@ +{ + "requires": true, + "lockfileVersion": 1, + "dependencies": { + "ajv": { + "version": "6.12.4", + "resolved": "https://registry.npmjs.org/ajv/-/ajv-6.12.4.tgz", + "integrity": "sha512-eienB2c9qVQs2KWexhkrdMLVDoIQCz5KSeLxwg9Lzk4DOfBtIK9PQwwufcsn1jjGuf9WZmqPMbGxOzfcuphJCQ==", + "requires": { + "fast-deep-equal": "^3.1.1", + "fast-json-stable-stringify": "^2.0.0", + "json-schema-traverse": "^0.4.1", + "uri-js": "^4.2.2" + } + }, + "asn1": { + "version": "0.2.4", + "resolved": "https://registry.npmjs.org/asn1/-/asn1-0.2.4.tgz", + "integrity": "sha512-jxwzQpLQjSmWXgwaCZE9Nz+glAG01yF1QnWgbhGwHI5A6FRIEY6IVqtHhIepHqI7/kyEyQEagBC5mBEFlIYvdg==", + "requires": { + "safer-buffer": "~2.1.0" + } + }, + "assert-plus": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/assert-plus/-/assert-plus-1.0.0.tgz", + "integrity": "sha1-8S4PPF13sLHN2RRpQuTpbB5N1SU=" + }, + "asynckit": { + "version": "0.4.0", + "resolved": "https://registry.npmjs.org/asynckit/-/asynckit-0.4.0.tgz", + "integrity": "sha1-x57Zf380y48robyXkLzDZkdLS3k=" + }, + "aws-sign2": { + "version": "0.7.0", + "resolved": "https://registry.npmjs.org/aws-sign2/-/aws-sign2-0.7.0.tgz", + "integrity": "sha1-tG6JCTSpWR8tL2+G1+ap8bP+dqg=" + }, + "aws4": { + "version": "1.10.1", + "resolved": "https://registry.npmjs.org/aws4/-/aws4-1.10.1.tgz", + "integrity": "sha512-zg7Hz2k5lI8kb7U32998pRRFin7zJlkfezGJjUc2heaD4Pw2wObakCDVzkKztTm/Ln7eiVvYsjqak0Ed4LkMDA==" + }, + "bcrypt-pbkdf": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/bcrypt-pbkdf/-/bcrypt-pbkdf-1.0.2.tgz", + "integrity": "sha1-pDAdOJtqQ/m2f/PKEaP2Y342Dp4=", + "requires": { + "tweetnacl": "^0.14.3" + } + }, + "caseless": { + "version": "0.12.0", + "resolved": "https://registry.npmjs.org/caseless/-/caseless-0.12.0.tgz", + "integrity": "sha1-G2gcIf+EAzyCZUMJBolCDRhxUdw=" + }, + "combined-stream": { + "version": "1.0.8", + "resolved": "https://registry.npmjs.org/combined-stream/-/combined-stream-1.0.8.tgz", + "integrity": "sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==", + "requires": { + "delayed-stream": "~1.0.0" + } + }, + "core-util-is": { + "version": "1.0.2", + "resolved": "https://registry.npmjs.org/core-util-is/-/core-util-is-1.0.2.tgz", + "integrity": "sha1-tf1UIgqivFq1eqtxQMlAdUUDwac=" + }, + "dashdash": { + "version": "1.14.1", + "resolved": "https://registry.npmjs.org/dashdash/-/dashdash-1.14.1.tgz", + "integrity": "sha1-hTz6D3y+L+1d4gMmuN1YEDX24vA=", + "requires": { + "assert-plus": "^1.0.0" + } + }, + "delayed-stream": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/delayed-stream/-/delayed-stream-1.0.0.tgz", + "integrity": "sha1-3zrhmayt+31ECqrgsp4icrJOxhk=" + }, + "ecc-jsbn": { + "version": "0.1.2", + "resolved": "https://registry.npmjs.org/ecc-jsbn/-/ecc-jsbn-0.1.2.tgz", + "integrity": "sha1-OoOpBOVDUyh4dMVkt1SThoSamMk=", + "requires": { + "jsbn": "~0.1.0", + "safer-buffer": "^2.1.0" + } + }, + "extend": { + "version": "3.0.2", + "resolved": "https://registry.npmjs.org/extend/-/extend-3.0.2.tgz", + "integrity": "sha512-fjquC59cD7CyW6urNXK0FBufkZcoiGG80wTuPujX590cB5Ttln20E2UB4S/WARVqhXffZl2LNgS+gQdPIIim/g==" + }, + "extsprintf": { + "version": "1.3.0", + "resolved": "https://registry.npmjs.org/extsprintf/-/extsprintf-1.3.0.tgz", + "integrity": "sha1-lpGEQOMEGnpBT4xS48V06zw+HgU=" + }, + "fast-deep-equal": { + "version": "3.1.3", + "resolved": "https://registry.npmjs.org/fast-deep-equal/-/fast-deep-equal-3.1.3.tgz", + "integrity": "sha512-f3qQ9oQy9j2AhBe/H9VC91wLmKBCCU/gDOnKNAYG5hswO7BLKj09Hc5HYNz9cGI++xlpDCIgDaitVs03ATR84Q==" + }, + "fast-json-stable-stringify": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/fast-json-stable-stringify/-/fast-json-stable-stringify-2.1.0.tgz", + "integrity": "sha512-lhd/wF+Lk98HZoTCtlVraHtfh5XYijIjalXck7saUtuanSDyLMxnHhSXEDJqHxD7msR8D0uCmqlkwjCV8xvwHw==" + }, + "forever-agent": { + "version": "0.6.1", + "resolved": "https://registry.npmjs.org/forever-agent/-/forever-agent-0.6.1.tgz", + "integrity": "sha1-+8cfDEGt6zf5bFd60e1C2P2sypE=" + }, + "form-data": { + "version": "2.3.3", + "resolved": "https://registry.npmjs.org/form-data/-/form-data-2.3.3.tgz", + "integrity": "sha512-1lLKB2Mu3aGP1Q/2eCOx0fNbRMe7XdwktwOruhfqqd0rIJWwN4Dh+E3hrPSlDCXnSR7UtZ1N38rVXm+6+MEhJQ==", + "requires": { + "asynckit": "^0.4.0", + "combined-stream": "^1.0.6", + "mime-types": "^2.1.12" + } + }, + "getpass": { + "version": "0.1.7", + "resolved": "https://registry.npmjs.org/getpass/-/getpass-0.1.7.tgz", + "integrity": "sha1-Xv+OPmhNVprkyysSgmBOi6YhSfo=", + "requires": { + "assert-plus": "^1.0.0" + } + }, + "har-schema": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/har-schema/-/har-schema-2.0.0.tgz", + "integrity": "sha1-qUwiJOvKwEeCoNkDVSHyRzW37JI=" + }, + "har-validator": { + "version": "5.1.5", + "resolved": "https://registry.npmjs.org/har-validator/-/har-validator-5.1.5.tgz", + "integrity": "sha512-nmT2T0lljbxdQZfspsno9hgrG3Uir6Ks5afism62poxqBM6sDnMEuPmzTq8XN0OEwqKLLdh1jQI3qyE66Nzb3w==", + "requires": { + "ajv": "^6.12.3", + "har-schema": "^2.0.0" + } + }, + "http-signature": { + "version": "1.2.0", + "resolved": "https://registry.npmjs.org/http-signature/-/http-signature-1.2.0.tgz", + "integrity": "sha1-muzZJRFHcvPZW2WmCruPfBj7rOE=", + "requires": { + "assert-plus": "^1.0.0", + "jsprim": "^1.2.2", + "sshpk": "^1.7.0" + } + }, + "is-typedarray": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/is-typedarray/-/is-typedarray-1.0.0.tgz", + "integrity": "sha1-5HnICFjfDBsR3dppQPlgEfzaSpo=" + }, + "isstream": { + "version": "0.1.2", + "resolved": "https://registry.npmjs.org/isstream/-/isstream-0.1.2.tgz", + "integrity": "sha1-R+Y/evVa+m+S4VAOaQ64uFKcCZo=" + }, + "jsbn": { + "version": "0.1.1", + "resolved": "https://registry.npmjs.org/jsbn/-/jsbn-0.1.1.tgz", + "integrity": "sha1-peZUwuWi3rXyAdls77yoDA7y9RM=" + }, + "json-schema": { + "version": "0.2.3", + "resolved": "https://registry.npmjs.org/json-schema/-/json-schema-0.2.3.tgz", + "integrity": "sha1-tIDIkuWaLwWVTOcnvT8qTogvnhM=" + }, + "json-schema-traverse": { + "version": "0.4.1", + "resolved": "https://registry.npmjs.org/json-schema-traverse/-/json-schema-traverse-0.4.1.tgz", + "integrity": "sha512-xbbCH5dCYU5T8LcEhhuh7HJ88HXuW3qsI3Y0zOZFKfZEHcpWiHU/Jxzk629Brsab/mMiHQti9wMP+845RPe3Vg==" + }, + "json-stringify-safe": { + "version": "5.0.1", + "resolved": "https://registry.npmjs.org/json-stringify-safe/-/json-stringify-safe-5.0.1.tgz", + "integrity": "sha1-Epai1Y/UXxmg9s4B1lcB4sc1tus=" + }, + "jsprim": { + "version": "1.4.1", + "resolved": "https://registry.npmjs.org/jsprim/-/jsprim-1.4.1.tgz", + "integrity": "sha1-MT5mvB5cwG5Di8G3SZwuXFastqI=", + "requires": { + "assert-plus": "1.0.0", + "extsprintf": "1.3.0", + "json-schema": "0.2.3", + "verror": "1.10.0" + } + }, + "mime-db": { + "version": "1.44.0", + "resolved": "https://registry.npmjs.org/mime-db/-/mime-db-1.44.0.tgz", + "integrity": "sha512-/NOTfLrsPBVeH7YtFPgsVWveuL+4SjjYxaQ1xtM1KMFj7HdxlBlxeyNLzhyJVx7r4rZGJAZ/6lkKCitSc/Nmpg==" + }, + "mime-types": { + "version": "2.1.27", + "resolved": "https://registry.npmjs.org/mime-types/-/mime-types-2.1.27.tgz", + "integrity": "sha512-JIhqnCasI9yD+SsmkquHBxTSEuZdQX5BuQnS2Vc7puQQQ+8yiP5AY5uWhpdv4YL4VM5c6iliiYWPgJ/nJQLp7w==", + "requires": { + "mime-db": "1.44.0" + } + }, + "oauth-sign": { + "version": "0.9.0", + "resolved": "https://registry.npmjs.org/oauth-sign/-/oauth-sign-0.9.0.tgz", + "integrity": "sha512-fexhUFFPTGV8ybAtSIGbV6gOkSv8UtRbDBnAyLQw4QPKkgNlsH2ByPGtMUqdWkos6YCRmAqViwgZrJc/mRDzZQ==" + }, + "performance-now": { + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/performance-now/-/performance-now-2.1.0.tgz", + "integrity": "sha1-Ywn04OX6kT7BxpMHrjZLSzd8nns=" + }, + "psl": { + "version": "1.8.0", + "resolved": "https://registry.npmjs.org/psl/-/psl-1.8.0.tgz", + "integrity": "sha512-RIdOzyoavK+hA18OGGWDqUTsCLhtA7IcZ/6NCs4fFJaHBDab+pDDmDIByWFRQJq2Cd7r1OoQxBGKOaztq+hjIQ==" + }, + "punycode": { + "version": "2.1.1", + "resolved": "https://registry.npmjs.org/punycode/-/punycode-2.1.1.tgz", + "integrity": "sha512-XRsRjdf+j5ml+y/6GKHPZbrF/8p2Yga0JPtdqTIY2Xe5ohJPD9saDJJLPvp9+NSBprVvevdXZybnj2cv8OEd0A==" + }, + "qs": { + "version": "6.5.2", + "resolved": "https://registry.npmjs.org/qs/-/qs-6.5.2.tgz", + "integrity": "sha512-N5ZAX4/LxJmF+7wN74pUD6qAh9/wnvdQcjq9TZjevvXzSUo7bfmw91saqMjzGS2xq91/odN2dW/WOl7qQHNDGA==" + }, + "request": { + "version": "2.88.2", + "resolved": "https://registry.npmjs.org/request/-/request-2.88.2.tgz", + "integrity": "sha512-MsvtOrfG9ZcrOwAW+Qi+F6HbD0CWXEh9ou77uOb7FM2WPhwT7smM833PzanhJLsgXjN89Ir6V2PczXNnMpwKhw==", + "requires": { + "aws-sign2": "~0.7.0", + "aws4": "^1.8.0", + "caseless": "~0.12.0", + "combined-stream": "~1.0.6", + "extend": "~3.0.2", + "forever-agent": "~0.6.1", + "form-data": "~2.3.2", + "har-validator": "~5.1.3", + "http-signature": "~1.2.0", + "is-typedarray": "~1.0.0", + "isstream": "~0.1.2", + "json-stringify-safe": "~5.0.1", + "mime-types": "~2.1.19", + "oauth-sign": "~0.9.0", + "performance-now": "^2.1.0", + "qs": "~6.5.2", + "safe-buffer": "^5.1.2", + "tough-cookie": "~2.5.0", + "tunnel-agent": "^0.6.0", + "uuid": "^3.3.2" + } + }, + "safe-buffer": { + "version": "5.2.1", + "resolved": "https://registry.npmjs.org/safe-buffer/-/safe-buffer-5.2.1.tgz", + "integrity": "sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ==" + }, + "safer-buffer": { + "version": "2.1.2", + "resolved": "https://registry.npmjs.org/safer-buffer/-/safer-buffer-2.1.2.tgz", + "integrity": "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg==" + }, + "sshpk": { + "version": "1.16.1", + "resolved": "https://registry.npmjs.org/sshpk/-/sshpk-1.16.1.tgz", + "integrity": "sha512-HXXqVUq7+pcKeLqqZj6mHFUMvXtOJt1uoUx09pFW6011inTMxqI8BA8PM95myrIyyKwdnzjdFjLiE6KBPVtJIg==", + "requires": { + "asn1": "~0.2.3", + "assert-plus": "^1.0.0", + "bcrypt-pbkdf": "^1.0.0", + "dashdash": "^1.12.0", + "ecc-jsbn": "~0.1.1", + "getpass": "^0.1.1", + "jsbn": "~0.1.0", + "safer-buffer": "^2.0.2", + "tweetnacl": "~0.14.0" + } + }, + "tough-cookie": { + "version": "2.5.0", + "resolved": "https://registry.npmjs.org/tough-cookie/-/tough-cookie-2.5.0.tgz", + "integrity": "sha512-nlLsUzgm1kfLXSXfRZMc1KLAugd4hqJHDTvc2hDIwS3mZAfMEuMbc03SujMF+GEcpaX/qboeycw6iO8JwVv2+g==", + "requires": { + "psl": "^1.1.28", + "punycode": "^2.1.1" + } + }, + "tunnel-agent": { + "version": "0.6.0", + "resolved": "https://registry.npmjs.org/tunnel-agent/-/tunnel-agent-0.6.0.tgz", + "integrity": "sha1-J6XeoGs2sEoKmWZ3SykIaPD8QP0=", + "requires": { + "safe-buffer": "^5.0.1" + } + }, + "tweetnacl": { + "version": "0.14.5", + "resolved": "https://registry.npmjs.org/tweetnacl/-/tweetnacl-0.14.5.tgz", + "integrity": "sha1-WuaBd/GS1EViadEIr6k/+HQ/T2Q=" + }, + "uri-js": { + "version": "4.4.0", + "resolved": "https://registry.npmjs.org/uri-js/-/uri-js-4.4.0.tgz", + "integrity": "sha512-B0yRTzYdUCCn9n+F4+Gh4yIDtMQcaJsmYBDsTSG8g/OejKBodLQ2IHfN3bM7jUsRXndopT7OIXWdYqc1fjmV6g==", + "requires": { + "punycode": "^2.1.0" + } + }, + "uuid": { + "version": "3.4.0", + "resolved": "https://registry.npmjs.org/uuid/-/uuid-3.4.0.tgz", + "integrity": "sha512-HjSDRw6gZE5JMggctHBcjVak08+KEVhSIiDzFnT9S9aegmp85S/bReBVTb4QTFaRNptJ9kuYaNhnbNEOkbKb/A==" + }, + "verror": { + "version": "1.10.0", + "resolved": "https://registry.npmjs.org/verror/-/verror-1.10.0.tgz", + "integrity": "sha1-OhBcoXBTr1XW4nDB+CiGguGNpAA=", + "requires": { + "assert-plus": "^1.0.0", + "core-util-is": "1.0.2", + "extsprintf": "^1.2.0" + } + } + } +}