fix bug

[nhentai.git] / nhentai / parser.py

diff --git a/nhentai/parser.py b/nhentai/parser.py
index e9cb4c56a5c085ce6d139d5046934022e3c9e6b2..deb40e2497f3496730fbcc27bb6be6ca25f4b7db 100644 (file)
--- a/nhentai/parser.py
+++ b/nhentai/parser.py
@@ -1,19 +1,20 @@
 # coding: utf-8
-from __future__ import print_function
-import sys
+from __future__ import unicode_literals, print_function
+
+from bs4 import BeautifulSoup
 import re
 import requests
-from bs4 import BeautifulSoup
-import constant
-from logger import logger
 from tabulate import tabulate
 
+import nhentai.constant as constant
+from nhentai.logger import logger
+
 
 def request(method, url, **kwargs):
     if not hasattr(requests, method):
         raise AttributeError('\'requests\' object has no attribute \'{0}\''.format(method))
 
-    return requests.__dict__[method](url, proxies=constant.PROXY, **kwargs)
+    return requests.__dict__[method](url, proxies=constant.PROXY, verify=False, **kwargs)
 
 
 def doujinshi_parser(id_):
@@ -30,9 +31,9 @@ def doujinshi_parser(id_):
         response = request('get', url).content
     except Exception as e:
         logger.critical(str(e))
-        sys.exit()
+        exit(1)
 
-    html = BeautifulSoup(response)
+    html = BeautifulSoup(response, 'html.parser')
     doujinshi_info = html.find('div', attrs={'id': 'info'})
 
     title = doujinshi_info.find('h1').text
@@ -42,10 +43,11 @@ def doujinshi_parser(id_):
     doujinshi['subtitle'] = subtitle.text if subtitle else ''
 
     doujinshi_cover = html.find('div', attrs={'id': 'cover'})
-    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img['src'])
+    img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png)$', doujinshi_cover.a.img.attrs['data-src'])
     if not img_id:
         logger.critical('Tried yo get image id failed')
-        sys.exit()
+        exit(1)
+
     doujinshi['img_id'] = img_id.group(1)
     doujinshi['ext'] = img_id.group(2)
 
@@ -80,7 +82,7 @@ def search_parser(keyword, page):
         logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
         exit(1)
 
-    html = BeautifulSoup(response)
+    html = BeautifulSoup(response, 'html.parser')
     doujinshi_search_result = html.find_all('div', attrs={'class': 'gallery'})
     for doujinshi in doujinshi_search_result:
         doujinshi_container = doujinshi.find('div', attrs={'class': 'caption'})
@@ -88,13 +90,16 @@ def search_parser(keyword, page):
         title = (title[:85] + '..') if len(title) > 85 else title
         id_ = re.search('/g/(\d+)/', doujinshi.a['href']).group(1)
         result.append({'id': id_, 'title': title})
+    if not result:
+        logger.warn('Not found anything of keyword {}'.format(keyword))
+
     return result
 
 
 def print_doujinshi(doujinshi_list):
     if not doujinshi_list:
         return
-    doujinshi_list = [i.values() for i in doujinshi_list]
+    doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
     headers = ['id', 'doujinshi']
     logger.info('Search Result\n' +
                 tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))