def get_entries(url, source, weekday, series, team, httpproxy=None):
"The function is used to parse feed and extract information"
feed = parse_feed(url, set_user_agent=True, httpproxy=httpproxy)
entries = []
for i in feed.entries:
entries.append({
'source':
source,
'weekday':
weekday,
'series':
series,
'team':
team,
'title':
i.title,
'page_link':
i.link,
'pubdate':
to_iso_utc(i.published, "%a, %d %b %Y %H:%M:%S %Z"),
'episode':
extract_episode(i.title),
'download_link':
i.enclosures[0].href,
'link_type':
'torrent'
})
return entries
def checkup(args):
config = merge_args_yaml(args)
initialize_db()
initialize_tasks()
for item_key in config['tasks']:
item = Item(config, item_key)
if config['chosenitem'] != None:
if not item.series in config['chosenitem']:
continue
if config['usenet']:
entries = item.get_entries()
for entry in entries:
if not has_entry(entry) and calculate_timegone(
entry['pubdate']) < 90 * 86400:
if entry['episode'] != None:
update_db(entry)
else:
item.write_sh(entry)
if config['usedatebase']:
episode_nums = set()
for root, dirs, files in os.walk(
os.path.join(config['download_path'], item_key)):
for name in files:
episode_nums.add(extract_episode(name))
episode_nums.discard(None)
print(item_key, episode_nums)
entries = query_all_by_series(item.series)
for entry in entries:
if entry['episode'] not in episode_nums:
item.write_sh(entry)
def checkup(args):
config = merge_args_yaml(args)
initialize_db()
initialize_tasks()
for item_key in config['tasks']:
item = Item(config,item_key)
if config['chosenitem'] != None:
if not item.series in config['chosenitem']:
continue
if config['usenet']:
entries = item.get_entries()
for entry in entries:
if not has_entry(entry) and calculate_timegone(entry['pubdate']) < 90*86400:
if entry['episode'] != None:
update_db(entry)
else:
item.write_sh(entry)
if config['usedatebase']:
episode_nums = set()
for root,dirs,files in os.walk(os.path.join(config['download_path'],item_key)):
for name in files:
episode_nums.add(extract_episode(name))
episode_nums.discard(None)
print(item_key,episode_nums)
entries = query_all_by_series(item.series)
for entry in entries:
if entry['episode'] not in episode_nums:
item.write_sh(entry)
def get_entries(url,source,weekday,series,team,httpproxy=None):
page = parse_page(url, set_user_agent=True, httpproxy=httpproxy)
entries = []
soup = BeautifulSoup(page.content, 'html.parser')
items = soup.find('tbody',id='data_list').find_all('tr')
for i in items:
title = i.find('td',style="text-align:left;").text.strip()
download_link = i.find('td',style="text-align:left;").a['href']
datetuple = re.search('(\w{4})/(\w{2})/(\w{2})',download_link).groups()
timetuple = re.search('(\w{2}):(\w{2})',
i.find_all('td')[-1].text).groups()
pubdate_local = "%s %s:00 +0800" % (' '.join(reversed(datetuple)),
':'.join(timetuple))
entries.append({
'source':source,
'weekday':weekday,
'series':series,
'team':team,
'title': title,
'page_link': ('http://share.xfsub.com:88/' +
i.find('a',target="_blank")['href']),
'pubdate': to_iso_utc(pubdate_local,"%d %m %Y %H:%M:%S %z"),
'episode': extract_episode(title),
'download_link': download_link,
'link_type': 'torrent'
})
return entries
def get_entries(url,source,weekday,series,team,httpproxy=None):
"The function is used to parse feed and extract information"
feed = parse_feed(url, set_user_agent=True, httpproxy=httpproxy)
entries = []
for i in feed.entries:
entries.append({
'source':source,
'weekday':weekday,
'series':series,
'team':team,
'title': i.title,
'page_link': i.link,
'pubdate': to_iso_utc(i.published,"%a, %d %b %Y %H:%M:%S %Z"),
'episode': extract_episode(i.title),
'download_link': i.enclosures[0].href,
'link_type': 'torrent'
})
return entries
def get_episodenums_by_series(series):
"""获得episodenums
Args:
series type: string
Returns:
episode_nums type: set
"""
episode_nums = set()
with sqlite3.connect(DATEBASE) as conn:
cur = conn.cursor()
cur.execute('SELECT title FROM updates WHERE series=?;', (series, ))
t = cur.fetchall()
from rssparser.tackles import extract_episode
for i in t:
episode_nums.add(extract_episode(name))
episode_nums.discard(None)
return episode_nums
def get_episodenums_by_series(series):
"""获得episodenums
Args:
series type: string
Returns:
episode_nums type: set
"""
episode_nums = set()
with sqlite3.connect(DATEBASE) as conn:
cur = conn.cursor()
cur.execute('SELECT title FROM updates WHERE series=?;',(series,))
t = cur.fetchall()
from rssparser.tackles import extract_episode
for i in t:
episode_nums.add(extract_episode(name))
episode_nums.discard(None)
return episode_nums
def get_entries(url, source, weekday, series, team, httpproxy=None):
page = parse_page(url, set_user_agent=True, httpproxy=httpproxy)
entries = []
soup = BeautifulSoup(page.content, 'html.parser')
items = soup.find('tbody', id='data_list').find_all('tr')
for i in items:
title = i.find('td', style="text-align:left;").text.strip()
download_link = i.find('td', style="text-align:left;").a['href']
datetuple = re.search('(\w{4})/(\w{2})/(\w{2})',
download_link).groups()
timetuple = re.search('(\w{2}):(\w{2})',
i.find_all('td')[-1].text).groups()
pubdate_local = "%s %s:00 +0800" % (' '.join(
reversed(datetuple)), ':'.join(timetuple))
entries.append({
'source':
source,
'weekday':
weekday,
'series':
series,
'team':
team,
'title':
title,
'page_link': ('http://share.xfsub.com:88/' +
i.find('a', target="_blank")['href']),
'pubdate':
to_iso_utc(pubdate_local, "%d %m %Y %H:%M:%S %z"),
'episode':
extract_episode(title),
'download_link':
download_link,
'link_type':
'torrent'
})
return entries