multithreading download

hentai/cmdline.py

@@ -1 +1,11 @@
-__author__ = 'ricter'
+from optparse import OptionParser
+
+
+def cmd_parser():
+    parser = OptionParser()
+    parser.add_option('--search', type='string', dest='keyword', action='store')
+    parser.add_option('--download', dest='is_download', action='store_true')
+    parser.add_option('--id', type='int', dest='id', action='store')
+
+    args, _ = parser.parse_args()
+    return args

hentai/constant.py

@@ -1 +1,4 @@
-__author__ = 'ricter'
+SCHEMA = 'http://'
+URL = '%snhentai.net' % SCHEMA
+DETAIL_URL = '%s/g' % URL
+IMAGE_URL = '%si.nhentai.net/galleries' % SCHEMA

hentai/dojinshi.py

@@ -1 +1,40 @@
-__author__ = 'ricter'
+import Queue
+from constant import DETAIL_URL, IMAGE_URL
+
+
+class Dojinshi(object):
+    def __init__(self, name=None, subtitle=None, id=None, pages=0):
+        self.name = name
+        self.subtitle = subtitle
+        self.id = id
+        self.pages = pages
+        self.downloader = None
+        self.url = '%s/%d' % (DETAIL_URL, self.id)
+
+    def __repr__(self):
+        return '<Dojinshi: %s>' % self.name
+
+    def show(self):
+        print 'Dojinshi: %s' % self.name
+        print 'Subtitle: %s' % self.subtitle
+        print 'URL: %s' % self.url
+        print 'Pages: %d' % self.pages
+
+    def download(self):
+        if self.downloader:
+            download_queue = Queue.Queue()
+            for i in xrange(1, self.pages + 1):
+                download_queue.put('%s/%d/%d.jpg' % (IMAGE_URL, self.id, i))
+            self.downloader.download(download_queue)
+        else:
+            raise Exception('Downloader has not be loaded')
+
+
+if __name__ == '__main__':
+    test = Dojinshi(name='test hentai dojinshi', id=1)
+    print test
+    test.show()
+    try:
+        test.download()
+    except Exception, e:
+        print 'Exception: %s' % str(e)

hentai/downloader.py

@@ -1 +1,37 @@
-__author__ = 'ricter'
+import threading
+import Queue
+
+
+class Downloader(object):
+    def __init__(self):
+        self.threads = []
+
+    def _download(self, queue):
+        while True:
+            if not queue.qsize():
+                queue.task_done()
+                break
+            try:
+                url = queue.get(False)
+                print 'Downloading: %s' % url
+            except Queue.Empty:
+                break
+
+    def download(self, queue):
+        for i in range(10):
+            _ = threading.Thread(target=self._download, args=(queue, ))
+            self.threads.append(_)
+
+        for i in self.threads:
+            i.start()
+
+        for i in self.threads:
+            i.join()
+
+
+if __name__ == '__main__':
+    d = Downloader()
+    q = Queue.Queue()
+    for i in range(0, 50):
+        q.put(i)
+    d.download(q)

hentai/parser.py

@@ -1 +1,39 @@
-__author__ = 'ricter'
+import re
+import requests
+from bs4 import BeautifulSoup
+from constant import DETAIL_URL
+
+
+dojinshi_fields = ['Artists:']
+
+
+def dojinshi_parser(id):
+    if not isinstance(id, (int, )) or (isinstance(id, (str, )) and not id.isdigit()):
+        raise Exception('Dojinshi id(%s) is not valid' % str(id))
+    id = int(id)
+    dojinshi = dict()
+    dojinshi['id'] = id
+    url = '%s/%d/' % (DETAIL_URL, id)
+
+    response = requests.get(url).content
+    html = BeautifulSoup(response)
+    dojinshi_info = html.find('div', attrs={'id': 'info'})
+
+    title = dojinshi_info.find('h1').text
+    subtitle = dojinshi_info.find('h2')
+
+    dojinshi['name'] = title
+    dojinshi['subtitle'] = subtitle.text if subtitle else ''
+
+    pages = 0
+    for _ in dojinshi_info.find_all('div', class_=''):
+        pages = re.search('([\d]+) pages', _.text)
+        if pages:
+            pages = pages.group(1)
+            break
+    dojinshi['pages'] = int(pages)
+    return dojinshi
+
+
+if __name__ == '__main__':
+    print dojinshi_parser(32271)