def _get_show_ids(self):
"""Get the ``dict`` of show ids per series by querying the `shows.php` page.
:return: show id per series, lower case and without quotes.
:rtype: dict
# patch: add punctuation cleaning
"""
# get the show page
logger.info('Getting show ids')
r = self.retry(lambda: self.session.get(self.server_url + 'shows.php',
timeout=10))
r.raise_for_status()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# populate the show ids
show_ids = {}
for show in soup.select('td.version > h3 > a[href^="/show/"]'):
show_clean = self.clean_punctuation(show.text.lower())
try:
show_id = int(show['href'][6:])
except ValueError:
continue
show_ids[show_clean] = show_id
match = series_year_re.match(show_clean)
if match.group(2) and match.group(1) not in show_ids:
# year found, also add it without year
show_ids[match.group(1)] = show_id
logger.debug('Found %d show ids', len(show_ids))
return show_ids
def _get_show_ids(self):
"""Get the ``dict`` of show ids per series by querying the `shows.php` page.
:return: show id per series, lower case and without quotes.
:rtype: dict
# patch: add punctuation cleaning
"""
# get the show page
logger.info('Getting show ids')
r = self.session.get(self.server_url + 'shows.php', timeout=10)
r.raise_for_status()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# populate the show ids
show_ids = {}
for show in soup.select('td.version > h3 > a[href^="/show/"]'):
show_clean = self.clean_punctuation(show.text.lower())
show_id = int(show['href'][6:])
show_ids[show_clean] = show_id
match = series_year_re.match(show_clean)
if match.group(2) and match.group(1) not in show_ids:
# year found, also add it without year
show_ids[match.group(1)] = show_id
logger.debug('Found %d show ids', len(show_ids))
return show_ids
def _search_show_id(self, series, year=None):
"""Search the show id from the `series` and `year`.
:param string series: series of the episode.
:param year: year of the series, if any.
:type year: int or None
:return: the show id, if found.
:rtype: int or None
# patch: add punctuation cleaning
"""
# build the params
series_year = '%s (%d)' % (series, year) if year is not None else series
params = {'search': series_year, 'Submit': 'Search'}
# make the search
logger.info('Searching show ids with %r', params)
r = self.session.get(self.server_url + 'search.php', params=params, timeout=10)
r.raise_for_status()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# get the suggestion
suggestion = soup.select('span.titulo > a[href^="/show/"]')
if not suggestion:
logger.warning('Show id not found: no suggestion')
return None
if not self.full_clean(suggestion[0].i.text.lower()) == self.full_clean(series_year.lower()):
logger.warning('Show id not found: suggestion does not match')
return None
show_id = int(suggestion[0]['href'][6:])
logger.debug('Found show id %d', show_id)
return show_id
def _search_show_id(self, series, year=None):
"""Search the show id from the `series` and `year`.
:param string series: series of the episode.
:param year: year of the series, if any.
:type year: int or None
:return: the show id, if found.
:rtype: int or None
# patch: add punctuation cleaning
"""
# build the params
series_year = '%s (%d)' % (series, year) if year is not None else series
params = {'search': series_year, 'Submit': 'Search'}
# make the search
logger.info('Searching show ids with %r', params)
r = self.session.get(self.server_url + 'search.php', params=params, timeout=10)
r.raise_for_status()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# get the suggestion
suggestion = soup.select('span.titulo > a[href^="/show/"]')
if not suggestion:
logger.warning('Show id not found: no suggestion')
return None
if not self.full_clean(suggestion[0].i.text.lower()) == self.full_clean(series_year.lower()):
logger.warning('Show id not found: suggestion does not match')
return None
show_id = int(suggestion[0]['href'][6:])
logger.debug('Found show id %d', show_id)
return show_id
def query(self, series, season, year=None, country=None):
# patch: fix logging
# get the show id
show_id = self.get_show_id(series, year, country)
if show_id is None:
logger.error('No show id found for %r (%r)', series, {'year': year, 'country': country})
return []
# get the page of the season of the show
logger.info('Getting the page of show id %d, season %d', show_id, season)
r = self.session.get(self.server_url + 'show/%d' % show_id, params={'season': season}, timeout=10)
r.raise_for_status()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# loop over subtitle rows
header = soup.select('#header font')
if header:
match = series_year_re.match(header[0].text.strip()[:-10])
series = match.group('series')
year = int(match.group('year')) if match.group('year') else None
subtitles = []
for row in soup.select('tr.epeven'):
cells = row('td')
# ignore incomplete subtitles
status = cells[5].text
if status != 'Completed':
logger.debug('Ignoring subtitle with status %s', status)
continue
# read the item
language = Language.fromaddic7ed(cells[3].text)
hearing_impaired = bool(cells[6].text)
page_link = self.server_url + cells[2].a['href'][1:]
season = int(cells[0].text)
episode = int(cells[1].text)
title = cells[2].text
version = cells[4].text
download_link = cells[9].a['href'][1:]
subtitle = PatchedAddic7edSubtitle(language, hearing_impaired, page_link, series, season, episode, title, year,
version, download_link)
logger.debug('Found subtitle %r', subtitle)
subtitles.append(subtitle)
return subtitles
def query(self, show_id, series, season, year=None, country=None):
# patch: fix logging
# get the page of the season of the show
logger.info('Getting the page of show id %d, season %d', show_id, season)
r = self.session.get(self.server_url + 'ajax_loadShow.php',
params={'show': show_id, 'season': season},
timeout=10,
headers={
"referer": "%sshow/%s" % (self.server_url, show_id),
"X-Requested-With": "XMLHttpRequest"
}
)
r.raise_for_status()
if r.status_code == 304:
raise TooManyRequests()
if not r.content:
# Provider wrongful return a status of 304 Not Modified with an empty content
# raise_for_status won't raise exception for that status code
logger.error('No data returned from provider')
return []
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# loop over subtitle rows
subtitles = []
for row in soup.select('tr.epeven'):
cells = row('td')
# ignore incomplete subtitles
status = cells[5].text
if status != 'Completed':
logger.debug('Ignoring subtitle with status %s', status)
continue
# read the item
language = Language.fromaddic7ed(cells[3].text)
hearing_impaired = bool(cells[6].text)
page_link = self.server_url + cells[2].a['href'][1:]
season = int(cells[0].text)
episode = int(cells[1].text)
title = cells[2].text
version = cells[4].text
download_link = cells[9].a['href'][1:]
subtitle = self.subtitle_class(language, hearing_impaired, page_link, series, season, episode, title,
year,
version, download_link)
logger.debug('Found subtitle %r', subtitle)
subtitles.append(subtitle)
soup.decompose()
soup = None
return subtitles
def _get_show_ids(self):
"""Get the ``dict`` of show ids per series by querying the `shows.php` page.
:return: show id per series, lower case and without quotes.
:rtype: dict
# patch: add punctuation cleaning
"""
# get the show page
logger.info('Getting show ids')
region.set(self.last_show_ids_fetch_key, datetime.datetime.now())
r = self.session.get(self.server_url + 'shows.php', timeout=10)
r.raise_for_status()
# LXML parser seems to fail when parsing Addic7ed.com HTML markup.
# Last known version to work properly is 3.6.4 (next version, 3.7.0, fails)
# Assuming the site's markup is bad, and stripping it down to only contain what's needed.
show_cells = re.findall(show_cells_re, r.content)
if show_cells:
soup = ParserBeautifulSoup(
b''.join(show_cells).decode('utf-8', 'ignore'),
['lxml', 'html.parser'])
else:
# If RegEx fails, fall back to original r.text and use 'html.parser'
soup = ParserBeautifulSoup(r.text, ['html.parser'])
# populate the show ids
show_ids = {}
shows = soup.select('td > h3 > a[href^="/show/"]')
for show in shows:
show_clean = sanitize(show.text,
default_characters=self.sanitize_characters)
try:
show_id = int(show['href'][6:])
except ValueError:
continue
show_ids[show_clean] = show_id
match = series_year_re.match(show_clean)
if match and match.group(2) and match.group(1) not in show_ids:
# year found, also add it without year
show_ids[match.group(1)] = show_id
soup.decompose()
soup = None
logger.debug('Found %d show ids', len(show_ids))
if not show_ids:
raise Exception("Addic7ed: No show IDs found!")
return show_ids
def query(self, series, season, year=None, country=None):
# patch: fix logging
# get the show id
show_id = self.get_show_id(series, year, country)
if show_id is None:
logger.error('No show id found for %r (%r)', series, {
'year': year,
'country': country
})
return []
# get the page of the season of the show
logger.info('Getting the page of show id %d, season %d', show_id,
season)
r = self.retry(
lambda: self.session.get(self.server_url + 'show/%d' % show_id,
params={'season': season},
timeout=10))
r.raise_for_status()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
# loop over subtitle rows
subtitles = []
for row in soup.select('tr.epeven'):
cells = row('td')
# ignore incomplete subtitles
status = cells[5].text
if status != 'Completed':
logger.debug('Ignoring subtitle with status %s', status)
continue
# read the item
language = Language.fromaddic7ed(cells[3].text)
hearing_impaired = bool(cells[6].text)
page_link = self.server_url + cells[2].a['href'][1:]
season = int(cells[0].text)
episode = int(cells[1].text)
title = cells[2].text
version = cells[4].text
download_link = cells[9].a['href'][1:]
subtitle = PatchedAddic7edSubtitle(language, hearing_impaired,
page_link, series, season,
episode, title, year, version,
download_link)
logger.debug('Found subtitle %r', subtitle)
subtitles.append(subtitle)
return subtitles
def _search_show_id(self, series, year=None):
"""Search the show id from the `series` and `year`.
:param str series: series of the episode.
:param year: year of the series, if any.
:type year: int
:return: the show id, if found.
:rtype: int
"""
# addic7ed doesn't support search with quotes
series = series.replace('\'', ' ')
# build the params
series_year = '%s %d' % (series, year) if year is not None else series
params = {'search': series_year, 'Submit': 'Search'}
# make the search
logger.info('Searching show ids with %r', params)
r = self.session.get(self.server_url + 'search.php',
params=params,
timeout=10)
r.raise_for_status()
if r.status_code == 304:
raise TooManyRequests()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
suggestion = None
# get the suggestion
try:
suggestion = soup.select('span.titulo > a[href^="/show/"]')
if not suggestion:
logger.warning('Show id not found: no suggestion')
return None
if not sanitize(suggestion[0].i.text.replace('\'', ' '),
default_characters=self.sanitize_characters) == \
sanitize(series_year, default_characters=self.sanitize_characters):
logger.warning('Show id not found: suggestion does not match')
return None
show_id = int(suggestion[0]['href'][6:])
logger.debug('Found show id %d', show_id)
return show_id
finally:
if suggestion:
suggestion.decompose()
soup.decompose()
soup = None
def _get_show_ids(self):
"""Get the ``dict`` of show ids per series by querying the `shows.php` page.
:return: show id per series, lower case and without quotes.
:rtype: dict
# patch: add punctuation cleaning
"""
# get the show page
logger.info('Getting show ids')
r = self.session.get(self.server_url + 'shows.php', timeout=10)
r.raise_for_status()
# LXML parser seems to fail when parsing Addic7ed.com HTML markup.
# Last known version to work properly is 3.6.4 (next version, 3.7.0, fails)
# Assuming the site's markup is bad, and stripping it down to only contain what's needed.
show_cells = re.findall(show_cells_re, r.content)
if show_cells:
soup = ParserBeautifulSoup(b''.join(show_cells), ['lxml', 'html.parser'])
else:
# If RegEx fails, fall back to original r.content and use 'html.parser'
soup = ParserBeautifulSoup(r.content, ['html.parser'])
# populate the show ids
show_ids = {}
for show in soup.select('td > h3 > a[href^="/show/"]'):
show_clean = sanitize(show.text, default_characters=self.sanitize_characters)
try:
show_id = int(show['href'][6:])
except ValueError:
continue
show_ids[show_clean] = show_id
match = series_year_re.match(show_clean)
if match and match.group(2) and match.group(1) not in show_ids:
# year found, also add it without year
show_ids[match.group(1)] = show_id
soup.decompose()
soup = None
logger.debug('Found %d show ids', len(show_ids))
return show_ids
def _search_show_id(self, series, year=None):
"""Search the show id from the `series` and `year`.
:param str series: series of the episode.
:param year: year of the series, if any.
:type year: int
:return: the show id, if found.
:rtype: int
"""
# addic7ed doesn't support search with quotes
series = series.replace('\'', ' ')
# build the params
series_year = '%s %d' % (series, year) if year is not None else series
params = {'search': series_year, 'Submit': 'Search'}
# make the search
logger.info('Searching show ids with %r', params)
# currently addic7ed searches via srch.php from the front page, then a re-search is needed which calls
# search.php
for endpoint in (
"srch.php",
"search.php",
):
headers = None
if endpoint == "search.php":
headers = {"referer": self.server_url + "srch.php"}
r = self.session.get(self.server_url + endpoint,
params=params,
timeout=10,
headers=headers)
r.raise_for_status()
if r.text and "Sorry, your search" not in r.text:
break
time.sleep(4)
if r.status_code == 304:
raise TooManyRequests()
soup = ParserBeautifulSoup(r.text, ['lxml', 'html.parser'])
suggestion = None
# get the suggestion
try:
suggestion = soup.select('span.titulo > a[href^="/show/"]')
if not suggestion:
logger.warning('Show id not found: no suggestion')
return None
if not sanitize(suggestion[0].i.text.replace('\'', ' '),
default_characters=self.sanitize_characters) == \
sanitize(series_year, default_characters=self.sanitize_characters):
logger.warning('Show id not found: suggestion does not match')
return None
show_id = int(suggestion[0]['href'][6:])
logger.debug('Found show id %d', show_id)
return show_id
finally:
soup.decompose()
soup = None
def _search_show_id(self, series, year=None):
"""Search the show id from the `series` and `year`.
:param str series: series of the episode.
:param year: year of the series, if any.
:type year: int
:return: the show id, if found.
:rtype: int
"""
# addic7ed doesn't support search with quotes
series = series.replace('\'', ' ')
# build the params
series_year = '%s %d' % (series, year) if year is not None else series
params = {'search': series_year, 'Submit': 'Search'}
# make the search
logger.info('Searching show ids with %r', params)
# currently addic7ed searches via srch.php from the front page, then a re-search is needed which calls
# search.php
for endpoint in ("srch.php", "search.php",):
headers = None
if endpoint == "search.php":
headers = {
"referer": self.server_url + "srch.php"
}
r = self.session.get(self.server_url + endpoint, params=params, timeout=10, headers=headers)
r.raise_for_status()
if r.content and "Sorry, your search" not in r.content:
break
time.sleep(4)
if r.status_code == 304:
raise TooManyRequests()
soup = ParserBeautifulSoup(r.content, ['lxml', 'html.parser'])
suggestion = None
# get the suggestion
try:
suggestion = soup.select('span.titulo > a[href^="/show/"]')
if not suggestion:
logger.warning('Show id not found: no suggestion')
return None
if not sanitize(suggestion[0].i.text.replace('\'', ' '),
default_characters=self.sanitize_characters) == \
sanitize(series_year, default_characters=self.sanitize_characters):
logger.warning('Show id not found: suggestion does not match')
return None
show_id = int(suggestion[0]['href'][6:])
logger.debug('Found show id %d', show_id)
return show_id
finally:
soup.decompose()
soup = None
