.gitignore

@@ -1,9 +1,6 @@
 *.part
 *.pyc
 *.log
-
-# output
 set.yaml
 tag.json
 output.csv
-torrents

LICENSE

@@ -1,121 +0,0 @@
-Creative Commons Legal Code
-
-CC0 1.0 Universal
-
-    CREATIVE COMMONS CORPORATION IS NOT A LAW FIRM AND DOES NOT PROVIDE
-    LEGAL SERVICES. DISTRIBUTION OF THIS DOCUMENT DOES NOT CREATE AN
-    ATTORNEY-CLIENT RELATIONSHIP. CREATIVE COMMONS PROVIDES THIS
-    INFORMATION ON AN "AS-IS" BASIS. CREATIVE COMMONS MAKES NO WARRANTIES
-    REGARDING THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS
-    PROVIDED HEREUNDER, AND DISCLAIMS LIABILITY FOR DAMAGES RESULTING FROM
-    THE USE OF THIS DOCUMENT OR THE INFORMATION OR WORKS PROVIDED
-    HEREUNDER.
-
-Statement of Purpose
-
-The laws of most jurisdictions throughout the world automatically confer
-exclusive Copyright and Related Rights (defined below) upon the creator
-and subsequent owner(s) (each and all, an "owner") of an original work of
-authorship and/or a database (each, a "Work").
-
-Certain owners wish to permanently relinquish those rights to a Work for
-the purpose of contributing to a commons of creative, cultural and
-scientific works ("Commons") that the public can reliably and without fear
-of later claims of infringement build upon, modify, incorporate in other
-works, reuse and redistribute as freely as possible in any form whatsoever
-and for any purposes, including without limitation commercial purposes.
-These owners may contribute to the Commons to promote the ideal of a free
-culture and the further production of creative, cultural and scientific
-works, or to gain reputation or greater distribution for their Work in
-part through the use and efforts of others.
-
-For these and/or other purposes and motivations, and without any
-expectation of additional consideration or compensation, the person
-associating CC0 with a Work (the "Affirmer"), to the extent that he or she
-is an owner of Copyright and Related Rights in the Work, voluntarily
-elects to apply CC0 to the Work and publicly distribute the Work under its
-terms, with knowledge of his or her Copyright and Related Rights in the
-Work and the meaning and intended legal effect of CC0 on those rights.
-
-1. Copyright and Related Rights. A Work made available under CC0 may be
-protected by copyright and related or neighboring rights ("Copyright and
-Related Rights"). Copyright and Related Rights include, but are not
-limited to, the following:
-
-  i. the right to reproduce, adapt, distribute, perform, display,
-     communicate, and translate a Work;
- ii. moral rights retained by the original author(s) and/or performer(s);
-iii. publicity and privacy rights pertaining to a person's image or
-     likeness depicted in a Work;
- iv. rights protecting against unfair competition in regards to a Work,
-     subject to the limitations in paragraph 4(a), below;
-  v. rights protecting the extraction, dissemination, use and reuse of data
-     in a Work;
- vi. database rights (such as those arising under Directive 96/9/EC of the
-     European Parliament and of the Council of 11 March 1996 on the legal
-     protection of databases, and under any national implementation
-     thereof, including any amended or successor version of such
-     directive); and
-vii. other similar, equivalent or corresponding rights throughout the
-     world based on applicable law or treaty, and any national
-     implementations thereof.
-
-2. Waiver. To the greatest extent permitted by, but not in contravention
-of, applicable law, Affirmer hereby overtly, fully, permanently,
-irrevocably and unconditionally waives, abandons, and surrenders all of
-Affirmer's Copyright and Related Rights and associated claims and causes
-of action, whether now known or unknown (including existing as well as
-future claims and causes of action), in the Work (i) in all territories
-worldwide, (ii) for the maximum duration provided by applicable law or
-treaty (including future time extensions), (iii) in any current or future
-medium and for any number of copies, and (iv) for any purpose whatsoever,
-including without limitation commercial, advertising or promotional
-purposes (the "Waiver"). Affirmer makes the Waiver for the benefit of each
-member of the public at large and to the detriment of Affirmer's heirs and
-successors, fully intending that such Waiver shall not be subject to
-revocation, rescission, cancellation, termination, or any other legal or
-equitable action to disrupt the quiet enjoyment of the Work by the public
-as contemplated by Affirmer's express Statement of Purpose.
-
-3. Public License Fallback. Should any part of the Waiver for any reason
-be judged legally invalid or ineffective under applicable law, then the
-Waiver shall be preserved to the maximum extent permitted taking into
-account Affirmer's express Statement of Purpose. In addition, to the
-extent the Waiver is so judged Affirmer hereby grants to each affected
-person a royalty-free, non transferable, non sublicensable, non exclusive,
-irrevocable and unconditional license to exercise Affirmer's Copyright and
-Related Rights in the Work (i) in all territories worldwide, (ii) for the
-maximum duration provided by applicable law or treaty (including future
-time extensions), (iii) in any current or future medium and for any number
-of copies, and (iv) for any purpose whatsoever, including without
-limitation commercial, advertising or promotional purposes (the
-"License"). The License shall be deemed effective as of the date CC0 was
-applied by Affirmer to the Work. Should any part of the License for any
-reason be judged legally invalid or ineffective under applicable law, such
-partial invalidity or ineffectiveness shall not invalidate the remainder
-of the License, and in such case Affirmer hereby affirms that he or she
-will not (i) exercise any of his or her remaining Copyright and Related
-Rights in the Work or (ii) assert any associated claims and causes of
-action with respect to the Work, in either case contrary to Affirmer's
-express Statement of Purpose.
-
-4. Limitations and Disclaimers.
-
- a. No trademark or patent rights held by Affirmer are waived, abandoned,
-    surrendered, licensed or otherwise affected by this document.
- b. Affirmer offers the Work as-is and makes no representations or
-    warranties of any kind concerning the Work, express, implied,
-    statutory or otherwise, including without limitation warranties of
-    title, merchantability, fitness for a particular purpose, non
-    infringement, or the absence of latent or other defects, accuracy, or
-    the present or absence of errors, whether or not discoverable, all to
-    the greatest extent permissible under applicable law.
- c. Affirmer disclaims responsibility for clearing rights of other persons
-    that may apply to the Work or any use thereof, including without
-    limitation any person's Copyright and Related Rights in the Work.
-    Further, Affirmer disclaims responsibility for obtaining any necessary
-    consents, permissions or other rights required for any use of the
-    Work.
- d. Affirmer understands and acknowledges that Creative Commons is not a
-    party to this document and has no duty or obligation with respect to
-    this CC0 or use of the Work.

README.md

@@ -1,29 +1,21 @@
 # nhentai-favorites
 
-Zǎoshang hǎo zhōngguó xiànzài wǒ yǒu BING CHILLING 🥶🍦 wǒ hěn xǐhuān BING CHILLING 🥶🍦 dànshì sùdù yǔ jīqíng 9 bǐ BING CHILLING 🥶🍦 sùdù yǔ jīqíng sùdù yǔ jīqíng 9 wǒ zuì xǐhuān suǒyǐ…xiànzài shì yīnyuè shíjiān zhǔnbèi 1 2 3 liǎng gè lǐbài yǐhòu sùdù yǔ jīqíng 9 ×3 bùyào wàngjì bùyào cu òguò jìdé qù diànyǐngyuàn kàn sùdù yǔ jīqíng 9 yīn wéi fēicháng hǎo diànyǐng dòngzuò fēicháng hǎo chàbùduō yīyàng BING CHILLING 🥶🍦zàijiàn 🥶🍦
-
-This project is a meme but it works until you have too many favorites to scrape and you get rate limited, or so I was told by a friend, not that I would know.
-
-## how to use?
-
+### how to use?
 `pip install -r ".\requirements.txt"`
-open `nfavorites.py` and it will close and generate set.yaml  
-open `set.yaml` and enter your cookie and useragent  
-final open nfavorites.py again and it will generate csv file if everything is ok
 
-## how to get my cookie?
 
-open <https://nhentai.net/favorites/>  
-open developer tools (F12)  
-switch to network tab  
-find favorites/ and click it  
-find cookie and useragent in request headers  
+Rename_me_set.yaml (rename)-> set.yaml  
+enter your cookie  
+open nfavorites.py
 
-## if something goes wrong in gettags
+### how to get my cookie?
 
-rename `example_tag.json` to `tag.json`  
-rerun `nfavorites.py`  
+open https://nhentai.net/favorites/  
+press F12  
+switch to network menu  
+find favorites/  
+copy cookie to set.yaml
 
-![alt text](https://github.com/phillychi3/nhentai-favorites/blob/main/image/nhentai_cookie_anduseranegt.png?raw=true)
+![alt text](https://github.com/phillychi3/nhentai-favorites/blob/main/image/nhentai_cookie.png?raw=true)
 
 ![alt text](https://github.com/phillychi3/nhentai-favorites/blob/main/image/csv.png?raw=true)

Rename_me_set.yaml

@@ -0,0 +1 @@
+cookid: ""

gettags.py

@@ -1,42 +1,23 @@
-from bs4 import BeautifulSoup
-import requests
+import gevent.monkey
+gevent.monkey.patch_all()
 import json
-import yaml
-
-
-URL = "https://nhentai.net/tags/"
-
-
-def wtfcloudflare(url, method="get", useragent=None, cookie=None, data=None):
-    session = requests.Session()
-    session.headers = {
-        'Referer': "https://nhentai.net/login/",
-        'User-Agent': useragent,
-        'Cookie': cookie,
-        'Accept-Language': 'en-US,en;q=0.9',
-        'Accept-Encoding': 'gzip, deflate, br',
-    }
-    if method == "get":
-        r = session.get(url)
-    elif method == "post":
-        r = session.post(url, data=data)
-    return r
 
+import fake_useragent
+import requests
+from bs4 import BeautifulSoup
 
+url = "https://nhentai.net/tags/"
 def get_tags():
-    with open('set.yaml', 'r') as f:
-        data = yaml.load(f, Loader=yaml.CLoader)
-        cookie = data["cookid"]
-        useragent = data["useragent"]
-        if cookie == "":
-            print("Please edit set.yaml")
-            exit()
     now = 1
     tagjson = {}
 
     while True:
-        data = wtfcloudflare(f"{URL}?page={now}",
-                             useragent=useragent, cookie=cookie)
+        ua = fake_useragent.UserAgent()
+        useragent = ua.random
+        headers = {
+            'user-agent': useragent
+        }
+        data = requests.get(f"{url}?page={now}", headers=headers)
         soup = BeautifulSoup(data.text, 'html.parser')
         tags = soup.find_all("a", class_='tag')
         if tags == []:
@@ -49,14 +30,9 @@ def get_tags():
             tagnumber.append(fixnum)
         for i in enumerate(tagnumber):
             tagjson[i[1]] = tagnames[i[0]]
-        print(f"page {now} done")
         now += 1
-    if tagjson == {}:
-        print("something wrong with your cookie or useragent")
-        exit()
     with open('tag.json', 'w') as f:
         json.dump(tagjson, f)
-    print("tag.json saved")
     return
 
 

nfavorites.py

@@ -3,28 +3,23 @@ from progress.spinner import PixelSpinner
 from bs4 import BeautifulSoup
 import yaml
 import requests
-import locale
+import fake_useragent
+import time
+import threading
+import random
+import queue
 import os
 import json
 import csv
+import gevent.monkey
+gevent.monkey.patch_all()
 
 
-if not os.path.isfile("set.yaml"):
-    with open('set.yaml', 'w') as f:
-        yaml.dump({"cookid": "", "useragent": ""}, f)
-    print("Please edit set.yaml")
-    exit()
-
 with open('set.yaml', 'r') as f:
-    data = yaml.load(f, Loader=yaml.CLoader)
-    cookie = data["cookid"]
-    useragent = data["useragent"]
-    if cookie == "":
-        print("Please edit set.yaml")
-        exit()
+    cookie = yaml.load(f, Loader=yaml.CLoader)["cookid"]
 # setting
-URL = "https://nhentai.net/favorites/"
-APIURL = "https://nhentai.net/api/gallery/"
+url = "https://nhentai.net/favorites/"
+apiurl = "https://nhentai.net/api/gallery/"
 table = [
     ["id", "name", "tags"]
 ]
@@ -32,79 +27,74 @@ now = 1
 allnumbers = []
 allnames = []
 alltags = []
-locate = locale.getdefaultlocale()[0]
-if locate == "zh_TW":
-    language = {
-        "nodata": "沒有發現離線資料 抓取中請稍後...",
-        "nodata2": "抓取完畢",
-        "usedata": "使用離線資料",
-        "getdata": "抓取資料中...",
-        "403": "403 錯誤，可能被 cloudflare 阻擋，請檢查 cookie 是否正確",
-        "nologin": "未登入，請先登入",
-        "done": "完成"
-    }
-else:
-    language = {
-        "nodata": "No offline data found, please wait a moment...",
-        "nodata2": "Done",
-        "usedata": "Use offline data",
-        "getdata": "Getting data...",
-        "403": "403 error, maby block by cloudflare , please check if the cookie is correct",
-        "nologin": "Not login, please login first",
-        "done": "Done"
-    }
-
-
-def banner():
-    data = r"               _           _        _         ___  _ \
-    _ __   ___| |__  _ __ | |_ __ _(_)        / __\/_\/\   /\ \
-    | '_ \ / _ \ '_ \| '_ \| __/ _` | |_____ / _\ //_\\ \ / / \
-    | | | |  __/ | | | | | | || (_| | |_____/ /  /  _  \ V /  \
-    |_| |_|\___|_| |_|_| |_|\__\__,_|_|     \/   \_/ \_/\_/   \
-                                                            "
-    print(data)
+ua = fake_useragent.UserAgent()
+useragent = ua.random
 
 # request
-
-
 def wtfcloudflare(url,method="get",data=None):
     session = requests.Session()
     session.headers = {
         'Referer': "https://nhentai.net/login/",
-        'User-Agent': useragent,
+        'User-Agent': "",
         'Cookie': cookie,
-        'Accept-Language': 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6',
-        'Accept-Encoding': 'gzip, deflate',
+        'Accept-Language': 'en-US,en;q=0.9',
+        'Accept-Encoding': 'gzip, deflate, br',
     }
     if method == "get":
         r = session.get(url)
     elif method == "post":
         r = session.post(url,data=data)
-    r.encoding = 'utf-8'
     return r
 
 
-def check_pass():
-    res = wtfcloudflare("https://nhentai.net/")
-    if res.status_code == 403:
-        print(language["403"])
-        exit()
+
+class gettagonline(threading.Thread):
+    def __init__(self, queue, number):
+        threading.Thread.__init__(self)
+        self.number = number
+        self.queue = queue
+
+    # def run(self):
+    #     while self.queue.qsize() > 0:
+    #         num = self.queue.get()
+    #         # print("get %d: %s" % (self.number, num))
+    #         ua = fake_useragent.UserAgent()
+    #         useragent = ua.random
+    #         headers = {
+    #             'user-agent': useragent
+    #         }
+    #         r = requests.get(apiurl + num, headers=headers)
+    #         data = r.json()
+    #         ctag = []
+    #         for i in enumerate(data['tags']):
+    #             ctag.append(i[1]['name'])
+    #         alltags.append(ctag)
+    #         time.sleep(random.uniform(0.5, 1))
 
 
-# --- main ---
-banner()
-check_pass()
+set1 = input("請問要使用離線資料嗎?(y/n)(默認為否)")
+if set1 == "y".lower() or set1 == "yes".lower():
     if not os.path.isfile("tag.json"):
-    print(language["nodata"])
+        print("沒有發現離線資料 抓取中請稍後...")
         get_tags()
-    print(language["nodata2"])
-print(language["usedata"])
-spinner = PixelSpinner(language["getdata"])
+        print("抓取完畢")
+    print("使用離線資料")
+else:
+    print("使用線上資料")
+    threadscount = input("請輸入要使用幾個線程(默認為5 不可超過10)")
+    if threadscount == "":
+        threadscount = 5
+    else:
+        try:
+            threadscount = int(threadscount)
+            if threadscount > 10:
+                threadscount = 10
+        except:
+            threadscount = 5
+
+spinner = PixelSpinner('抓取資料中...')
 while True:
-    data = wtfcloudflare(f"{URL}?page={now}")
-    if "Abandon all hope, ye who enter here" in data.text:
-        print(language["nologin"])
-        exit()
+    data = wtfcloudflare(f"{url}?page={now}")
     soup = BeautifulSoup(data.text, 'html.parser')
     book = soup.find_all("div", class_='gallery-favorite')
     if book == []:
@@ -123,6 +113,7 @@ while True:
     spinner.next()
 
 
+if set1 == "y".lower() or set1 == "yes".lower():
     with open('tag.json', 'r') as f:
         tagjson = json.load(f)
     for i in enumerate(allnumbers):
@@ -132,9 +123,23 @@ for i in enumerate(allnumbers):
                 tagstr += tagjson[j] + ", "
 
         table.append([i[1], allnames[i[0]], tagstr])
+else:
+    alltags = []  # 清空
+    get_tags_queue = queue.Queue()
+    threads = []
+    for i in allnumbers:
+        get_tags_queue.put(i)
+    for i in range(threadscount):
+        t = gettagonline(get_tags_queue, i)
+        t.start()
+        threads.append(t)
+    for t in threads:
+        t.join()
+
+    for i in enumerate(allnumbers):
+        table.append([i[1], allnames[i[0]], alltags[i[0]]])
 
 
 with open('output.csv', 'w', newline='', encoding="utf_8_sig") as csvfile:
     writer = csv.writer(csvfile)
     writer.writerows(table)
-print(language["done"])

requirements.txt

@@ -1,6 +1,6 @@
-# Automatically generated by https://github.com/damnever/pigar.
-
-beautifulsoup4
-progress
-PyYAML
-requests
+PyYAML == 5.4.1
+bs4 
+fake_useragent == 0.1.11
+gevent == 21.1.2
+progress == 1.6
+requests == 2.27.1

scraper.py

@@ -1,163 +0,0 @@
-from progress.spinner import PixelSpinner
-from bs4 import BeautifulSoup
-import yaml
-import requests
-import locale
-import os
-import json
-import csv
-
-if not os.path.isfile("set.yaml"):
-    with open('set.yaml', 'w') as f:
-        yaml.dump({"cookid": "", "useragent": ""}, f)
-    print("Please edit set.yaml")
-    exit()
-
-with open('set.yaml', 'r') as f:
-    data = yaml.load(f, Loader=yaml.CLoader)
-    cookie = data["cookid"]
-    useragent = data["useragent"]
-    if cookie == "":
-        print("Please edit set.yaml")
-        exit()
-# setting
-URL = "https://nhentai.net/favorites/"
-APIURL = "https://nhentai.net/api/gallery/"
-table = [
-    ["id", "name", "tags"]
-]
-now = 1
-allnumbers = []
-allnames = []
-alltags = []
-locate = locale.getdefaultlocale()[0]
-if locate == "zh_TW":
-    language = {
-        "nodata": "沒有發現離線資料 抓取中請稍後...",
-        "nodata2": "抓取完畢",
-        "usedata": "使用離線資料",
-        "getdata": "抓取資料中...",
-        "403": "403 錯誤，可能被 cloudflare 阻擋，請檢查 cookie 是否正確",
-        "nologin": "未登入，請先登入",
-        "done": "完成"
-    }
-else:
-    language = {
-        "nodata": "No offline data found, please wait a moment...",
-        "nodata2": "Done",
-        "usedata": "Use offline data",
-        "getdata": "Getting data...",
-        "403": "403 error, maby block by cloudflare , please check if the cookie is correct",
-        "nologin": "Not login, please login first",
-        "done": "Done"
-    }
-
-
-def banner():
-    data = r"               _           _        _         ___  _ \
-    _ __   ___| |__  _ __ | |_ __ _(_)        / __\/_\/\   /\ \
-    | '_ \ / _ \ '_ \| '_ \| __/ _` | |_____ / _\ //_\\ \ / / \
-    | | | |  __/ | | | | | | || (_| | |_____/ /  /  _  \ V /  \
-    |_| |_|\___|_| |_|_| |_|\__\__,_|_|     \/   \_/ \_/\_/   \
-                                                            "
-    print(data)
-
-def wtfcloudflare(url, method="get", data=None):
-    session = requests.Session()
-    session.headers = {
-        'Referer': "https://nhentai.net/login/",
-        'User-Agent': useragent,
-        'Cookie': cookie,
-        'Accept-Language': 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6',
-        'Accept-Encoding': 'gzip, deflate',
-    }
-    if method == "get":
-        r = session.get(url)
-    elif method == "post":
-        r = session.post(url, data=data)
-    r.encoding = 'utf-8'
-    return r
-
-def wtfcloudflare_t(url, method="get", data=None, useragent=None, cookie=None):
-    session = requests.Session()
-    session.headers = {
-        'Referer': "https://nhentai.net/login/",
-        'User-Agent': useragent,
-        'Cookie': cookie,
-        'Accept-Language': 'zh-TW,zh;q=0.9,en-US;q=0.8,en;q=0.7,zh-CN;q=0.6',
-        'Accept-Encoding': 'gzip, deflate',
-    }
-
-    if method == "get":
-        r = session.get(url, stream=True)  # Add stream=True for large/binary files
-    elif method == "post":
-        r = session.post(url, data=data, stream=True)  # stream=True for binary data
-    
-    r.raise_for_status()  # Check for request errors
-    return r
-
-
-def check_pass():
-    res = wtfcloudflare("https://nhentai.net/")
-    if res.status_code == 403:
-        print(language["403"])
-        exit()
-
-url_list  = []
-
-def build_id_list():
-    # Open and read the CSV file
-    with open('output.csv', 'r', encoding='utf-8-sig') as file:
-        reader = csv.DictReader(file)
-        
-        # Print out the headers to debug the issue
-        print(reader.fieldnames)  # This will show the exact header names
-        
-        # Iterate over each row in the CSV
-        for row in reader:
-            # Check if 'id' exists in the row, and if not, print the row for debugging
-            if 'id' in row:
-                formatted_url = f"https://nhentai.net/g/{row['id']}/download"
-                url_list.append(formatted_url)
-            else:
-                print(f"Row without 'id': {row}")
-
-banner()
-check_pass()
-build_id_list()
-
-def get_torrents():
-    with open('set.yaml', 'r') as f:
-        data = yaml.load(f, Loader=yaml.CLoader)
-        cookie = data["cookid"]
-        useragent = data["useragent"]
-        if cookie == "":
-            print("Please edit set.yaml")
-            exit()
-
-    for url in url_list:
-        torrent_url = url
-
-        # Call wtfcloudflare to download the torrent file
-        response = wtfcloudflare_t(torrent_url, useragent=useragent, cookie=cookie)
-
-        # Extract the ID from the URL for naming the file
-        torrent_id = url.split('/')[4]  # The ID is in the 4th segment of the URL
-        
-        # Define the output directory and file name
-        output_dir = "torrents"
-        os.makedirs(output_dir, exist_ok=True)  # Create the directory if it doesn't exist
-        torrent_path = os.path.join(output_dir, f"{torrent_id}.torrent")
-
-        # Save the torrent file to disk
-        with open(torrent_path, 'wb') as torrent_file:
-            for chunk in response.iter_content(chunk_size=8192):
-                if chunk:  # Filter out keep-alive chunks
-                    torrent_file.write(chunk)
-
-        print(f"Downloaded torrent: {torrent_path}")
-
-
-if __name__ == '__main__':
-    get_torrents()
-