# coding: utf-8
-from __future__ import unicode_literals, print_function
-import sys
import os
import re
import time
return result
-def favorites_parser(page_range=''):
+def favorites_parser(page=None):
result = []
html = BeautifulSoup(request('get', constant.FAV_URL).content, 'html.parser')
count = html.find('span', attrs={'class': 'count'})
return []
pages = int(count / 25)
- if pages:
- pages += 1 if count % (25 * pages) else 0
+ if page:
+ page_range_list = page
else:
- pages = 1
+ if pages:
+ pages += 1 if count % (25 * pages) else 0
+ else:
+ pages = 1
- logger.info('You have %d favorites in %d pages.' % (count, pages))
+ logger.info('You have %d favorites in %d pages.' % (count, pages))
- if os.getenv('DEBUG'):
- pages = 1
+ if os.getenv('DEBUG'):
+ pages = 1
- page_range_list = range(1, pages + 1)
- if page_range:
- logger.info('page range is {0}'.format(page_range))
- page_range_list = page_range_parser(page_range, pages)
+ page_range_list = range(1, pages + 1)
for page in page_range_list:
try:
return result
-def page_range_parser(page_range, max_page_num):
- pages = set()
- ranges = str.split(page_range, ',')
- for range_str in ranges:
- idx = range_str.find('-')
- if idx == -1:
- try:
- page = int(range_str)
- if page <= max_page_num:
- pages.add(page)
- except ValueError:
- logger.error('page range({0}) is not valid'.format(page_range))
- else:
- try:
- left = int(range_str[:idx])
- right = int(range_str[idx + 1:])
- if right > max_page_num:
- right = max_page_num
- for page in range(left, right + 1):
- pages.add(page)
- except ValueError:
- logger.error('page range({0}) is not valid'.format(page_range))
-
- return list(pages)
-
-
def doujinshi_parser(id_):
if not isinstance(id_, (int,)) and (isinstance(id_, (str,)) and not id_.isdigit()):
raise Exception('Doujinshi id({0}) is not valid'.format(id_))
try:
response = request('get', url)
- if response.status_code in (200,):
+ if response.status_code in (200, ):
response = response.content
+ elif response.status_code in (404,):
+ logger.error("Doujinshi with id {0} cannot be found".format(id_))
+ return []
else:
logger.debug('Slow down and retry ({}) ...'.format(id_))
time.sleep(1)
return doujinshi_parser(str(id_))
except Exception as e:
- logger.warn('Error: {}, ignored'.format(str(e)))
+ logger.warning('Error: {}, ignored'.format(str(e)))
return None
html = BeautifulSoup(response, 'html.parser')
doujinshi_info = html.find('div', attrs={'id': 'info'})
title = doujinshi_info.find('h1').text
+ pretty_name = doujinshi_info.find('h1').find('span', attrs={'class': 'pretty'}).text
subtitle = doujinshi_info.find('h2')
doujinshi['name'] = title
+ doujinshi['pretty_name'] = pretty_name
doujinshi['subtitle'] = subtitle.text if subtitle else ''
doujinshi_cover = html.find('div', attrs={'id': 'cover'})
- img_id = re.search('/galleries/([\d]+)/cover\.(jpg|png|gif)$', doujinshi_cover.a.img.attrs['data-src'])
+ img_id = re.search('/galleries/([0-9]+)/cover.(jpg|png|gif)$',
+ doujinshi_cover.a.img.attrs['data-src'])
ext = []
for i in html.find_all('div', attrs={'class': 'thumb-container'}):
doujinshi['img_id'] = img_id.group(1)
doujinshi['ext'] = ext
- pages = 0
for _ in doujinshi_info.find_all('div', class_='tag-container field-name'):
if re.search('Pages:', _.text):
pages = _.find('span', class_='name').string
result = _get_title_and_id(response)
if not result:
- logger.warn('Not found anything of keyword {}'.format(keyword))
+ logger.warning('Not found anything of keyword {}'.format(keyword))
return result
return
doujinshi_list = [(i['id'], i['title']) for i in doujinshi_list]
headers = ['id', 'doujinshi']
- logger.info('Search Result\n' +
+ logger.info('Search Result || Found %i doujinshis \n' % doujinshi_list.__len__() +
tabulate(tabular_data=doujinshi_list, headers=headers, tablefmt='rst'))
-def search_parser(keyword, sorting, page):
- logger.debug('Searching doujinshis using keywords {0}'.format(keyword))
- keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
+def search_parser(keyword, sorting, page, is_page_all=False):
+ # keyword = '+'.join([i.strip().replace(' ', '-').lower() for i in keyword.split(',')])
result = []
- i = 0
- while i < 5:
- try:
- url = request('get', url=constant.SEARCH_URL, params={'query': keyword, 'page': page, 'sort': sorting}).url
- response = request('get', url.replace('%2B', '+')).json()
- except Exception as e:
- i += 1
- if not i < 5:
+ response = None
+ if not page:
+ page = [1]
+
+ if is_page_all:
+ url = request('get', url=constant.SEARCH_URL, params={'query': keyword}).url
+ init_response = request('get', url.replace('%2B', '+')).json()
+ page = range(1, init_response['num_pages']+1)
+
+ total = '/{0}'.format(page[-1]) if is_page_all else ''
+ not_exists_persist = False
+ for p in page:
+ i = 0
+
+ logger.info('Searching doujinshis using keywords "{0}" on page {1}{2}'.format(keyword, p, total))
+ while i < 3:
+ try:
+ url = request('get', url=constant.SEARCH_URL, params={'query': keyword,
+ 'page': p, 'sort': sorting}).url
+ response = request('get', url.replace('%2B', '+')).json()
+ except Exception as e:
logger.critical(str(e))
- logger.warn('If you are in China, please configure the proxy to fu*k GFW.')
- exit(1)
- continue
- break
+ response = None
+ break
- if 'result' not in response:
- raise Exception('No result in response')
+ if response is None or 'result' not in response:
+ logger.warning('No result in response in page {}'.format(p))
+ if not_exists_persist is True:
+ break
+ continue
- for row in response['result']:
- title = row['title']['english']
- title = title[:85] + '..' if len(title) > 85 else title
- result.append({'id': row['id'], 'title': title})
+ for row in response['result']:
+ title = row['title']['english']
+ title = title[:85] + '..' if len(title) > 85 else title
+ result.append({'id': row['id'], 'title': title})
- if not result:
- logger.warn('No results for keywords {}'.format(keyword))
+ not_exists_persist = False
+ if not result:
+ logger.warning('No results for keywords {}'.format(keyword))
return result
projects / nhentai.git / blobdiff