diff --git a/recipes/slashdot.recipe b/recipes/slashdot.recipe index c7c68c3f1a..b10700a749 100644 --- a/recipes/slashdot.recipe +++ b/recipes/slashdot.recipe @@ -8,23 +8,36 @@ __copyright__ = '2009, Kovid Goyal edited by Huan T' from calibre.web.feeds.news import BasicNewsRecipe class Slashdot(BasicNewsRecipe): - title = u'Slashdot.org' - description = '''Tech news. WARNING: This recipe downloads a lot - of content and may result in your IP being banned from slashdot.org''' - oldest_article = 7 - simultaneous_downloads = 1 - delay = 3 - max_articles_per_feed = 100 - language = 'en' + title = u'Slashdot.org' + description = '''Tech news. WARNING: This recipe downloads a lot + of content and may result in your IP being banned from slashdot.org''' + oldest_article = 7 + simultaneous_downloads = 1 + delay = 3 + max_articles_per_feed = 100 + language = 'en' - __author__ = 'floweros edited by Huan T' - no_stylesheets = True -# keep_only_tags = [ -# dict(name='div',attrs={'class':'article'}), -# dict(name='div',attrs={'class':'commentTop'}), -# ] + __author__ = 'floweros edited by Huan T' + no_stylesheets = True + keep_only_tags = [ + dict(name='div',attrs={'id':'article'}), + dict(name='div',attrs={'class':['postBody' 'details']}), + dict(name='footer',attrs={'class':['clearfix meta article-foot']}), + dict(name='article',attrs={'class':['fhitem fhitem-story article usermode thumbs grid_24']}), + dict(name='dl',attrs={'class':'relatedPosts'}), + dict(name='h2',attrs={'class':'story'}), + dict(name='span',attrs={'class':'comments'}), + ] - feeds = [ + + remove_tags = [ + dict(name='aside',attrs={'id':'slashboxes'}), + dict(name='div',attrs={'class':'paginate'}), + dict(name='section',attrs={'id':'comments'}), + dict(name='span',attrs={'class':'topic'}), + ] + + feeds = [ (u'Slashdot', u'http://rss.slashdot.org/Slashdot/slashdot'), (u'/. IT', @@ -37,5 +50,3 @@ class Slashdot(BasicNewsRecipe): u'http://rss.slashdot.org/Slashdot/slashdotYourRightsOnline') ] - def get_article_url(self, article): - return article.get('feedburner_origlink', None) diff --git a/src/calibre/customize/builtins.py b/src/calibre/customize/builtins.py index d3b0b8409d..75c02c7e00 100644 --- a/src/calibre/customize/builtins.py +++ b/src/calibre/customize/builtins.py @@ -626,8 +626,9 @@ if test_eight_code: from calibre.ebooks.metadata.sources.amazon import Amazon from calibre.ebooks.metadata.sources.openlibrary import OpenLibrary from calibre.ebooks.metadata.sources.isbndb import ISBNDB + from calibre.ebooks.metadata.sources.overdrive import OverDrive - plugins += [GoogleBooks, Amazon, OpenLibrary, ISBNDB] + plugins += [GoogleBooks, Amazon, OpenLibrary, ISBNDB, OverDrive] # }}} else: diff --git a/src/calibre/ebooks/conversion/preprocess.py b/src/calibre/ebooks/conversion/preprocess.py index a1d5fa94d8..8822a39b87 100644 --- a/src/calibre/ebooks/conversion/preprocess.py +++ b/src/calibre/ebooks/conversion/preprocess.py @@ -399,7 +399,7 @@ class HTMLPreProcessor(object): (re.compile(u'˙\s*()*\s*Z', re.UNICODE), lambda match: u'Ż'), # If pdf printed from a browser then the header/footer has a reliable pattern - (re.compile(r'((?<=)\s*file:////?[A-Z].*
|file:////?[A-Z].*
(?=\s*
))', re.IGNORECASE), lambda match: ''), + (re.compile(r'((?<=)\s*file:/{2,4}[A-Z].*
|file:////?[A-Z].*
(?=\s*
))', re.IGNORECASE), lambda match: ''), # Center separator lines (re.compile(u'
\s*(?P([*#•✦=]+\s*)+)\s*
'), lambda match: '

\n

' + match.group(1) + '

'), diff --git a/src/calibre/ebooks/conversion/utils.py b/src/calibre/ebooks/conversion/utils.py index f1f2f87293..1546644f95 100644 --- a/src/calibre/ebooks/conversion/utils.py +++ b/src/calibre/ebooks/conversion/utils.py @@ -764,6 +764,7 @@ class HeuristicProcessor(object): # Multiple sequential blank paragraphs are merged with appropriate margins # If non-blank scene breaks exist they are center aligned and styled with appropriate margins. if getattr(self.extra_opts, 'format_scene_breaks', False): + html = re.sub('(?i)]*>\s*\s*', '

', html) html = self.detect_whitespace(html) html = self.detect_soft_breaks(html) blanks_count = len(self.any_multi_blank.findall(html)) diff --git a/src/calibre/ebooks/metadata/sources/base.py b/src/calibre/ebooks/metadata/sources/base.py index c9639bf531..37407a0656 100644 --- a/src/calibre/ebooks/metadata/sources/base.py +++ b/src/calibre/ebooks/metadata/sources/base.py @@ -274,26 +274,34 @@ class Source(Plugin): if authors: # Leave ' in there for Irish names - pat = re.compile(r'[-,:;+!@#$%^&*(){}.`~"\s\[\]/]') + remove_pat = re.compile(r'[,!@#$%^&*(){}`~"\s\[\]/]') + replace_pat = re.compile(r'[-+.:;]') if only_first_author: authors = authors[:1] for au in authors: + au = replace_pat.sub(' ', au) parts = au.split() if ',' in au: # au probably in ln, fn form parts = parts[1:] + parts[:1] for tok in parts: - tok = pat.sub('', tok).strip() + tok = remove_pat.sub('', tok).strip() if len(tok) > 2 and tok.lower() not in ('von', ): yield tok - def get_title_tokens(self, title): + def get_title_tokens(self, title, strip_joiners=True, strip_subtitle=False): ''' Take a title and return a list of tokens useful for an AND search query. - Excludes connectives and punctuation. + Excludes connectives(optionally) and punctuation. ''' if title: + # strip sub-titles + if strip_subtitle: + subtitle = re.compile(r'([\(\[\{].*?[\)\]\}]|[/:\\].*$)') + if len(subtitle.sub('', title)) > 1: + title = subtitle.sub('', title) + title_patterns = [(re.compile(pat, re.IGNORECASE), repl) for pat, repl in [ # Remove things like: (2010) (Omnibus) etc. @@ -305,17 +313,20 @@ class Source(Plugin): (r'(\d+),(\d+)', r'\1\2'), # Remove hyphens only if they have whitespace before them (r'(\s-)', ' '), - # Remove single quotes - (r"'", ''), + # Remove single quotes not followed by 's' + (r"'(?!s)", ''), # Replace other special chars with a space (r'''[:,;+!@#$%^&*(){}.`~"\s\[\]/]''', ' ') ]] + for pat, repl in title_patterns: title = pat.sub(repl, title) + tokens = title.split() for token in tokens: token = token.strip() - if token and token.lower() not in ('a', 'and', 'the'): + if token and (not strip_joiners or token.lower() not in ('a', + 'and', 'the', '&')): yield token def split_jobs(self, jobs, num): @@ -363,7 +374,11 @@ class Source(Plugin): def get_book_url(self, identifiers): ''' Return the URL for the book identified by identifiers at this source. - If no URL is found, return None. + This URL must be browseable to by a human using a browser. It is meant + to provide a clickable link for the user to easily visit the books page + at this source. + If no URL is found, return None. This method must be quick, either it + should construct the URL using a known URL scheme or use a cached URL. ''' return None diff --git a/src/calibre/ebooks/metadata/sources/identify.py b/src/calibre/ebooks/metadata/sources/identify.py index 1fb1a74679..6295efa0c0 100644 --- a/src/calibre/ebooks/metadata/sources/identify.py +++ b/src/calibre/ebooks/metadata/sources/identify.py @@ -433,7 +433,7 @@ def urls_from_identifiers(identifiers): # {{{ pass isbn = identifiers.get('isbn', None) if isbn: - ans.append(('ISBN', + ans.append((isbn, 'http://www.worldcat.org/search?q=bn%%3A%s&qt=advanced'%isbn)) return ans # }}} @@ -444,13 +444,18 @@ if __name__ == '__main__': # tests {{{ from calibre.ebooks.metadata.sources.test import (test_identify, title_test, authors_test) tests = [ + ( + {'title':'Magykal Papers', + 'authors':['Sage']}, + [title_test('The Magykal Papers', exact=True)], + ), + ( # An e-book ISBN not on Amazon, one of the authors is # unknown to Amazon {'identifiers':{'isbn': '9780307459671'}, 'title':'Invisible Gorilla', 'authors':['Christopher Chabris']}, - [title_test('The Invisible Gorilla', - exact=True), authors_test(['Christopher Chabris', 'Daniel Simons'])] + [title_test('The Invisible Gorilla', exact=True)] ), diff --git a/src/calibre/ebooks/metadata/sources/overdrive.py b/src/calibre/ebooks/metadata/sources/overdrive.py new file mode 100755 index 0000000000..26c90f08fe --- /dev/null +++ b/src/calibre/ebooks/metadata/sources/overdrive.py @@ -0,0 +1,439 @@ +#!/usr/bin/env python +from __future__ import (unicode_literals, division, absolute_import, + print_function) + +__license__ = 'GPL v3' +__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net' +__docformat__ = 'restructuredtext en' + +''' +Fetch metadata using Overdrive Content Reserve +''' +import re, random, mechanize, copy +from threading import RLock +from Queue import Queue, Empty + +from lxml import html +from lxml.html import soupparser + +from calibre.ebooks.metadata import check_isbn +from calibre.ebooks.metadata.sources.base import Source +from calibre.ebooks.metadata.book.base import Metadata +from calibre.ebooks.chardet import xml_to_unicode +from calibre.library.comments import sanitize_comments_html + +ovrdrv_data_cache = {} +cover_url_cache = {} +cache_lock = RLock() +base_url = 'http://search.overdrive.com/' + + +class OverDrive(Source): + + name = 'Overdrive' + description = _('Downloads metadata from Overdrive\'s Content Reserve') + + capabilities = frozenset(['identify', 'cover']) + touched_fields = frozenset(['title', 'authors', 'tags', 'pubdate', + 'comments', 'publisher', 'identifier:isbn', 'series', 'series_index', + 'language', 'identifier:overdrive']) + has_html_comments = True + supports_gzip_transfer_encoding = False + cached_cover_url_is_reliable = True + + def __init__(self, *args, **kwargs): + Source.__init__(self, *args, **kwargs) + self.prefs.defaults['ignore_fields'] =['tags', 'pubdate', 'comments', 'identifier:isbn', 'language'] + + def identify(self, log, result_queue, abort, title=None, authors=None, # {{{ + identifiers={}, timeout=30): + ovrdrv_id = identifiers.get('overdrive', None) + isbn = identifiers.get('isbn', None) + + br = self.browser + ovrdrv_data = self.to_ovrdrv_data(br, title, authors, ovrdrv_id) + if ovrdrv_data: + title = ovrdrv_data[8] + authors = ovrdrv_data[6] + mi = Metadata(title, authors) + self.parse_search_results(ovrdrv_data, mi) + if ovrdrv_id is None: + ovrdrv_id = ovrdrv_data[7] + if isbn is not None: + self.cache_isbn_to_identifier(isbn, ovrdrv_id) + + self.get_book_detail(br, ovrdrv_data[1], mi, ovrdrv_id, log) + + result_queue.put(mi) + + return None + # }}} + + def download_cover(self, log, result_queue, abort, # {{{ + title=None, authors=None, identifiers={}, timeout=30): + cached_url = self.get_cached_cover_url(identifiers) + if cached_url is None: + log.info('No cached cover found, running identify') + rq = Queue() + self.identify(log, rq, abort, title=title, authors=authors, + identifiers=identifiers) + if abort.is_set(): + return + results = [] + while True: + try: + results.append(rq.get_nowait()) + except Empty: + break + results.sort(key=self.identify_results_keygen( + title=title, authors=authors, identifiers=identifiers)) + for mi in results: + cached_url = self.get_cached_cover_url(mi.identifiers) + if cached_url is not None: + break + if cached_url is None: + log.info('No cover found') + return + + if abort.is_set(): + return + + ovrdrv_id = identifiers.get('overdrive', None) + br = self.browser + referer = self.get_base_referer()+'ContentDetails-Cover.htm?ID='+ovrdrv_id + req = mechanize.Request(cached_url) + req.add_header('referer', referer) + log('Downloading cover from:', cached_url) + try: + cdata = br.open_novisit(req, timeout=timeout).read() + result_queue.put((self, cdata)) + except: + log.exception('Failed to download cover from:', cached_url) + # }}} + + def get_cached_cover_url(self, identifiers): # {{{ + url = None + ovrdrv_id = identifiers.get('overdrive', None) + if ovrdrv_id is None: + isbn = identifiers.get('isbn', None) + if isbn is not None: + ovrdrv_id = self.cached_isbn_to_identifier(isbn) + if ovrdrv_id is not None: + url = self.cached_identifier_to_cover_url(ovrdrv_id) + + return url + # }}} + + def get_base_referer(self): # to be used for passing referrer headers to cover download + choices = [ + 'http://overdrive.chipublib.org/82DC601D-7DDE-4212-B43A-09D821935B01/10/375/en/', + 'http://emedia.clevnet.org/9D321DAD-EC0D-490D-BFD8-64AE2C96ECA8/10/241/en/', + 'http://singapore.lib.overdrive.com/F11D55BE-A917-4D63-8111-318E88B29740/10/382/en/', + 'http://ebooks.nypl.org/20E48048-A377-4520-BC43-F8729A42A424/10/257/en/', + 'http://spl.lib.overdrive.com/5875E082-4CB2-4689-9426-8509F354AFEF/10/335/en/' + ] + return choices[random.randint(0, len(choices)-1)] + + def format_results(self, reserveid, od_title, subtitle, series, publisher, creators, thumbimage, worldcatlink, formatid): + fix_slashes = re.compile(r'\\/') + thumbimage = fix_slashes.sub('/', thumbimage) + worldcatlink = fix_slashes.sub('/', worldcatlink) + cover_url = re.sub('(?P(Ima?g(eType-)?))200', '\g100', thumbimage) + social_metadata_url = base_url+'TitleInfo.aspx?ReserveID='+reserveid+'&FormatID='+formatid + series_num = '' + if not series: + if subtitle: + title = od_title+': '+subtitle + else: + title = od_title + else: + title = od_title + m = re.search("([0-9]+$)", subtitle) + if m: + series_num = float(m.group(1)) + return [cover_url, social_metadata_url, worldcatlink, series, series_num, publisher, creators, reserveid, title] + + def safe_query(self, br, query_url, post=''): + ''' + The query must be initialized by loading an empty search results page + this page attempts to set a cookie that Mechanize doesn't like + copy the cookiejar to a separate instance and make a one-off request with the temp cookiejar + ''' + goodcookies = br._ua_handlers['_cookies'].cookiejar + clean_cj = mechanize.CookieJar() + cookies_to_copy = [] + for cookie in goodcookies: + copied_cookie = copy.deepcopy(cookie) + cookies_to_copy.append(copied_cookie) + for copied_cookie in cookies_to_copy: + clean_cj.set_cookie(copied_cookie) + + if post: + br.open_novisit(query_url, post) + else: + br.open_novisit(query_url) + + br.set_cookiejar(clean_cj) + + def overdrive_search(self, br, q, title, author): + # re-initialize the cookiejar to so that it's clean + clean_cj = mechanize.CookieJar() + br.set_cookiejar(clean_cj) + q_query = q+'default.aspx/SearchByKeyword' + q_init_search = q+'SearchResults.aspx' + # get first author as string - convert this to a proper cleanup function later + author_tokens = list(self.get_author_tokens(author, + only_first_author=True)) + title_tokens = list(self.get_title_tokens(title, + strip_joiners=False, strip_subtitle=True)) + + if len(title_tokens) >= len(author_tokens): + initial_q = ' '.join(title_tokens) + xref_q = '+'.join(author_tokens) + else: + initial_q = ' '.join(author_tokens) + xref_q = '+'.join(title_tokens) + + q_xref = q+'SearchResults.svc/GetResults?iDisplayLength=50&sSearch='+xref_q + query = '{"szKeyword":"'+initial_q+'"}' + + # main query, requires specific Content Type header + req = mechanize.Request(q_query) + req.add_header('Content-Type', 'application/json; charset=utf-8') + br.open_novisit(req, query) + + # initiate the search without messing up the cookiejar + self.safe_query(br, q_init_search) + + # get the search results object + results = False + while results == False: + xreq = mechanize.Request(q_xref) + xreq.add_header('X-Requested-With', 'XMLHttpRequest') + xreq.add_header('Referer', q_init_search) + xreq.add_header('Accept', 'application/json, text/javascript, */*') + raw = br.open_novisit(xreq).read() + for m in re.finditer(ur'"iTotalDisplayRecords":(?P\d+).*?"iTotalRecords":(?P\d+)', raw): + if int(m.group('displayrecords')) >= 1: + results = True + elif int(m.group('totalrecords')) >= 1: + xref_q = '' + q_xref = q+'SearchResults.svc/GetResults?iDisplayLength=50&sSearch='+xref_q + elif int(m.group('totalrecords')) == 0: + return '' + + return self.sort_ovrdrv_results(raw, title, title_tokens, author, author_tokens) + + + def sort_ovrdrv_results(self, raw, title=None, title_tokens=None, author=None, author_tokens=None, ovrdrv_id=None): + close_matches = [] + raw = re.sub('.*?\[\[(?P.*?)\]\].*', '[[\g]]', raw) + results = eval(raw) + #print results + # The search results are either from a keyword search or a multi-format list from a single ID, + # sort through the results for closest match/format + if results: + for reserveid, od_title, subtitle, edition, series, publisher, format, formatid, creators, \ + thumbimage, shortdescription, worldcatlink, excerptlink, creatorfile, sorttitle, \ + availabletolibrary, availabletoretailer, relevancyrank, unknown1, unknown2, unknown3 in results: + #print "this record's title is "+od_title+", subtitle is "+subtitle+", author[s] are "+creators+", series is "+series + if ovrdrv_id is not None and int(formatid) in [1, 50, 410, 900]: + #print "overdrive id is not None, searching based on format type priority" + return self.format_results(reserveid, od_title, subtitle, series, publisher, + creators, thumbimage, worldcatlink, formatid) + else: + creators = creators.split(', ') + # if an exact match in a preferred format occurs + if (author and creators[0] == author[0]) and od_title == title and int(formatid) in [1, 50, 410, 900]: + return self.format_results(reserveid, od_title, subtitle, series, publisher, + creators, thumbimage, worldcatlink, formatid) + else: + close_title_match = False + close_author_match = False + for token in title_tokens: + if od_title.lower().find(token.lower()) != -1: + close_title_match = True + else: + close_title_match = False + break + for author in creators: + for token in author_tokens: + if author.lower().find(token.lower()) != -1: + close_author_match = True + else: + close_author_match = False + break + if close_author_match: + break + if close_title_match and close_author_match and int(formatid) in [1, 50, 410, 900] and thumbimage: + if subtitle and series: + close_matches.insert(0, self.format_results(reserveid, od_title, subtitle, series, publisher, creators, thumbimage, worldcatlink, formatid)) + else: + close_matches.append(self.format_results(reserveid, od_title, subtitle, series, publisher, creators, thumbimage, worldcatlink, formatid)) + if close_matches: + return close_matches[0] + else: + return '' + else: + return '' + + def overdrive_get_record(self, br, q, ovrdrv_id): + search_url = q+'SearchResults.aspx?ReserveID={'+ovrdrv_id+'}' + results_url = q+'SearchResults.svc/GetResults?sEcho=1&iColumns=18&sColumns=ReserveID%2CTitle%2CSubtitle%2CEdition%2CSeries%2CPublisher%2CFormat%2CFormatID%2CCreators%2CThumbImage%2CShortDescription%2CWorldCatLink%2CExcerptLink%2CCreatorFile%2CSortTitle%2CAvailableToLibrary%2CAvailableToRetailer%2CRelevancyRank&iDisplayStart=0&iDisplayLength=10&sSearch=&bEscapeRegex=true&iSortingCols=1&iSortCol_0=17&sSortDir_0=asc' + + # re-initialize the cookiejar to so that it's clean + clean_cj = mechanize.CookieJar() + br.set_cookiejar(clean_cj) + # get the base url to set the proper session cookie + br.open_novisit(q) + + # initialize the search + self.safe_query(br, search_url) + + # get the results + req = mechanize.Request(results_url) + req.add_header('X-Requested-With', 'XMLHttpRequest') + req.add_header('Referer', search_url) + req.add_header('Accept', 'application/json, text/javascript, */*') + raw = br.open_novisit(req) + raw = str(list(raw)) + clean_cj = mechanize.CookieJar() + br.set_cookiejar(clean_cj) + return self.sort_ovrdrv_results(raw, None, None, None, ovrdrv_id) + + + def find_ovrdrv_data(self, br, title, author, isbn, ovrdrv_id=None): + q = base_url + if ovrdrv_id is None: + return self.overdrive_search(br, q, title, author) + else: + return self.overdrive_get_record(br, q, ovrdrv_id) + + + + def to_ovrdrv_data(self, br, title=None, author=None, ovrdrv_id=None): + ''' + Takes either a title/author combo or an Overdrive ID. One of these + two must be passed to this function. + ''' + if ovrdrv_id is not None: + with cache_lock: + ans = ovrdrv_data_cache.get(ovrdrv_id, None) + if ans: + return ans + elif ans is False: + return None + else: + ovrdrv_data = self.find_ovrdrv_data(br, title, author, ovrdrv_id) + else: + try: + ovrdrv_data = self.find_ovrdrv_data(br, title, author, ovrdrv_id) + except: + import traceback + traceback.print_exc() + ovrdrv_data = None + with cache_lock: + ovrdrv_data_cache[ovrdrv_id] = ovrdrv_data if ovrdrv_data else False + + return ovrdrv_data if ovrdrv_data else False + + + def parse_search_results(self, ovrdrv_data, mi): + ''' + Parse the formatted search results from the initial Overdrive query and + add the values to the metadta. + + The list object has these values: + [cover_url[0], social_metadata_url[1], worldcatlink[2], series[3], series_num[4], + publisher[5], creators[6], reserveid[7], title[8]] + + ''' + ovrdrv_id = ovrdrv_data[7] + mi.set_identifier('overdrive', ovrdrv_id) + + if len(ovrdrv_data[3]) > 1: + mi.series = ovrdrv_data[3] + if ovrdrv_data[4]: + try: + mi.series_index = float(ovrdrv_data[4]) + except: + pass + mi.publisher = ovrdrv_data[5] + mi.authors = ovrdrv_data[6] + mi.title = ovrdrv_data[8] + cover_url = ovrdrv_data[0] + if cover_url: + self.cache_identifier_to_cover_url(ovrdrv_id, + cover_url) + + + def get_book_detail(self, br, metadata_url, mi, ovrdrv_id, log): + try: + raw = br.open_novisit(metadata_url).read() + except Exception, e: + if callable(getattr(e, 'getcode', None)) and \ + e.getcode() == 404: + return False + raise + raw = xml_to_unicode(raw, strip_encoding_pats=True, + resolve_entities=True)[0] + try: + root = soupparser.fromstring(raw) + except: + return False + + pub_date = root.xpath("//div/label[@id='ctl00_ContentPlaceHolder1_lblPubDate']/text()") + lang = root.xpath("//div/label[@id='ctl00_ContentPlaceHolder1_lblLanguage']/text()") + subjects = root.xpath("//div/label[@id='ctl00_ContentPlaceHolder1_lblSubjects']/text()") + ebook_isbn = root.xpath("//td/label[@id='ctl00_ContentPlaceHolder1_lblIdentifier']/text()") + desc = root.xpath("//div/label[@id='ctl00_ContentPlaceHolder1_lblDescription']/ancestor::div[1]") + + if pub_date: + from calibre.utils.date import parse_date + mi.pubdate = parse_date(pub_date[0].strip()) + if lang: + mi.language = lang[0].strip() + + if ebook_isbn: + #print "ebook isbn is "+str(ebook_isbn[0]) + isbn = check_isbn(ebook_isbn[0].strip()) + if isbn: + self.cache_isbn_to_identifier(isbn, ovrdrv_id) + mi.isbn = isbn + if subjects: + mi.tags = [tag.strip() for tag in subjects[0].split(',')] + + if desc: + desc = desc[0] + desc = html.tostring(desc, method='html', encoding=unicode).strip() + # remove all attributes from tags + desc = re.sub(r'<([a-zA-Z0-9]+)\s[^>]+>', r'<\1>', desc) + # Remove comments + desc = re.sub(r'(?s)', '', desc) + mi.comments = sanitize_comments_html(desc) + + return None + + +if __name__ == '__main__': + # To run these test use: + # calibre-debug -e src/calibre/ebooks/metadata/sources/overdrive.py + from calibre.ebooks.metadata.sources.test import (test_identify_plugin, + title_test, authors_test) + test_identify_plugin(OverDrive.name, + [ + + ( + {'title':'Foundation and Earth', + 'authors':['Asimov']}, + [title_test('Foundation and Earth', exact=True), + authors_test(['Isaac Asimov'])] + ), + + ( + {'title': 'Elephants', 'authors':['Agatha']}, + [title_test('Elephants Can Remember', exact=False), + authors_test(['Agatha Christie'])] + ), + ]) + diff --git a/src/calibre/gui2/metadata/single_download.py b/src/calibre/gui2/metadata/single_download.py index c4e13a90f8..a3ac777115 100644 --- a/src/calibre/gui2/metadata/single_download.py +++ b/src/calibre/gui2/metadata/single_download.py @@ -949,7 +949,7 @@ class CoverFetch(QDialog): # {{{ # }}} if __name__ == '__main__': - DEBUG_DIALOG = True + #DEBUG_DIALOG = True app = QApplication([]) d = FullFetch() d.start(title='great gatsby', authors=['fitzgerald'])