Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix chitanka store

Browse Source 
Update html parser to be consistent with the current version of the site.
This commit is contained in:
josdion 2021-02-21 01:00:56 +02:00
parent 8e98cb061f
commit 7d9ebf412d
1 changed files with 54 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

117
src/calibre/gui2/store/stores/chitanka_plugin.py
View File

@ -27,6 +27,44 @@ from calibre.gui2.store.search_result import SearchResult
from calibre.gui2.store.web_store_dialog import WebStoreDialog
def parse_book_page(doc, base_url, counter):
for data in doc.xpath('//div[@class="booklist"]/div/div'):
if counter <= 0:
break
id = ''.join(data.xpath('.//div[@class="media-body"]/a[@class="booklink"]/@href')).strip()
if not id:
continue
counter -= 1
s = SearchResult()
s.cover_url = 'http:' + ''.join(
data.xpath('.//div[@class="media-left"]/a[@class="booklink"]/div/img/@src')).strip()
s.title = ''.join(data.xpath('.//div[@class="media-body"]/a[@class="booklink"]/i/text()')).strip()
alternative_headline = data.xpath('.//div[@class="media-body"]/div[@itemprop="alternativeHeadline"]/text()')
if len(alternative_headline) > 0:
s.title = "{} ({})".format(s.title, ''.join(alternative_headline).strip())
s.author = ', '.join(data.xpath('.//div[@class="media-body"]/div[@class="bookauthor"]/span/a/text()')).strip(', ')
s.detail_item = id
s.drm = SearchResult.DRM_UNLOCKED
s.downloads['FB2'] = base_url + ''.join(data.xpath(
'.//div[@class="media-body"]/div[@class="download-links"]/div/a[contains(@class,"dl-fb2")]/@href')).strip().replace(
'.zip', '')
s.downloads['EPUB'] = base_url + ''.join(data.xpath(
'.//div[@class="media-body"]/div[@class="download-links"]/div/a[contains(@class,"dl-epub")]/@href')).strip().replace(
'.zip', '')
s.downloads['TXT'] = base_url + ''.join(data.xpath(
'.//div[@class="media-body"]/div[@class="download-links"]/div/a[contains(@class,"dl-txt")]/@href')).strip().replace(
'.zip', '')
s.formats = 'FB2, EPUB, TXT'
yield s
return counter
class ChitankaStore(BasicStoreConfig, StorePlugin):
def open(self, parent=None, detail_item=None, external=False):
@ -46,12 +84,10 @@ class ChitankaStore(BasicStoreConfig, StorePlugin):
d.exec_()
def search(self, query, max_results=10, timeout=60):
# check for cyrillic symbols before performing search
if isinstance(query, bytes):
query = query.decode('utf-8')
uquery = query.strip()
reObj = re.search(u'^[а-яА-Я\\d\\s]{3,}$', uquery)
if not reObj:
if len(query) < 3:
return
base_url = 'http://chitanka.info'
@ -64,73 +100,28 @@ class ChitankaStore(BasicStoreConfig, StorePlugin):
with closing(br.open(url, timeout=timeout)) as f:
f = f.read().decode('utf-8')
doc = html.fromstring(f)
counter = yield from parse_book_page(doc, base_url, counter)
if counter <= 0:
return
for data in doc.xpath('//ul[@class="superlist booklist"]/li'):
if counter <= 0:
break
id = ''.join(data.xpath('.//a[@class="booklink"]/@href')).strip()
if not id:
# search for author names
for data in doc.xpath('//ul[@class="superlist"][1]/li/dl/dt'):
author_url = ''.join(data.xpath('.//a[contains(@href,"/person/")]/@href'))
if author_url == '':
continue
counter -= 1
br2 = browser()
with closing(br2.open(base_url + author_url, timeout=timeout)) as f:
f = f.read().decode('utf-8')
doc = html.fromstring(f)
counter = yield from parse_book_page(doc, base_url, counter)
if counter <= 0:
break
s = SearchResult()
s.cover_url = ''.join(data.xpath('.//a[@class="booklink"]/img/@src')).strip()
s.title = ''.join(data.xpath('.//a[@class="booklink"]/i/text()')).strip()
s.author = ''.join(data.xpath('.//span[@class="bookauthor"]/a/text()')).strip()
s.detail_item = id
s.drm = SearchResult.DRM_UNLOCKED
s.downloads['FB2'] = base_url + ''.join(data.xpath('.//a[@class="dl dl-fb2"]/@href')).strip().replace('.zip', '')
s.downloads['EPUB'] = base_url + ''.join(data.xpath('.//a[@class="dl dl-epub"]/@href')).strip().replace('.zip', '')
s.downloads['TXT'] = base_url + ''.join(data.xpath('.//a[@class="dl dl-txt"]/@href')).strip().replace('.zip', '')
s.formats = 'FB2, EPUB, TXT, SFB'
yield s
except HTTPError as e:
if e.code == 404:
return
else:
raise
# search for author names
for data in doc.xpath('//ul[@class="superlist"][1]/li/dl/dt'):
author_url = ''.join(data.xpath('.//a[contains(@href,"/person/")]/@href'))
if author_url == '':
continue
if counter <= 0:
break
br2 = browser()
with closing(br2.open(base_url + author_url, timeout=timeout)) as f:
if counter <= 0:
break
f = f.read().decode('utf-8')
doc2 = html.fromstring(f)
# search for book title
for data in doc2.xpath('//ul[@class="superlist booklist"]/li'):
if counter <= 0:
break
id = ''.join(data.xpath('.//a[@class="booklink"]/@href')).strip()
if not id:
continue
title = ''.join(data.xpath('.//a[@class="booklink"]/i/text()')).strip()
author = ''.join(data.xpath('.//span[@class="bookauthor"]/a/text()')).strip()
if title.lower().find(query.lower()) == -1 and author.lower().find(query.lower()) == -1:
continue
counter -= 1
s = SearchResult()
s.cover_url = ''.join(data.xpath('.//a[@class="booklink"]/img/@src')).strip()
s.title = title
s.author = author
s.detail_item = id
s.drm = SearchResult.DRM_UNLOCKED
s.downloads['FB2'] = base_url + ''.join(data.xpath('.//a[@class="dl dl-fb2"]/@href')).strip().replace('.zip', '')
s.downloads['EPUB'] = base_url + ''.join(data.xpath('.//a[@class="dl dl-epub"]/@href')).strip().replace('.zip', '')
s.downloads['TXT'] = base_url + ''.join(data.xpath('.//a[@class="dl dl-txt"]/@href')).strip().replace('.zip', '')
s.formats = 'FB2, EPUB, TXT, SFB'
yield s