def _parse_one_chapter(self, element, url):
item = ChapterListItem()
item['title'] = element.xpath('./a/text()')[0]
item['url'] = urljoin(url, element.xpath('./a/@href')[0])
update_str = element.xpath('./a/@title')[0]
item['updated_at'] = update_str.rsplit(' ', 1)[0].split(u'：')[-1]
item['word_count'] = int(update_str.rsplit(' ', 1)[-1].split(u'：')[-1])
return item
def parse_chapter_list(self, content, url):
try:
sel = etree.HTML(content)
except ValueError:
raise ValueError("can't parse any volume")
chapters = sel.xpath('//ul[@class="ListRow"]/li/a')[:-2]
chapter_ordinal = 1
for chapter in chapters:
try:
item = ChapterListItem()
item['url'] = urljoin(url, chapter.xpath('./@href')[0])
item['title'] = chapter.xpath('./text()')[0]
item['updated_at'] = None
item['word_count'] = 0
item['chapter_ordinal'] = chapter_ordinal
chapter_ordinal += 1
yield item
except Exception as e:
self.logger.error(e)
def parse_chapter_list(self, content, url):
try:
sel = etree.HTML(content)
except ValueError:
raise ValueError("can't parse any volume")
chapters = sel.xpath('//div[@id="list"]/dl/dd')[9:]
self.logger.debug(chapters)
chapter_ordinal = 1
for chapter in chapters:
item = ChapterListItem()
try:
item['title'] = chapter.xpath('./a/text()')[0]
item['url'] = chapter.xpath('./a/@href')[0]
item['updated_at'] = ''
item['word_count'] = 0
item['chapter_ordinal'] = chapter_ordinal
chapter_ordinal += 1
yield item
except Exception as e:
self.logger.error(e)
def parse_chapter_list(self, content, url):
try:
sel = etree.HTML(content)
except ValueError:
raise ValueError("can't parse any volume")
chapters = sel.xpath('//ul[@class="catalog-list cl"]/li')
chapter_ordinal = 1
for chapter in chapters:
if chapter.xpath('./i[@class="iconfont"]'):
break
item = ChapterListItem()
try:
item['title'] = chapter.xpath('./a/text()')[0]
item['url'] = urljoin(url, chapter.xpath('./a/@href')[0])
item['updated_at'] = ''
item['word_count'] = 0
item['chapter_ordinal'] = chapter_ordinal
chapter_ordinal += 1
yield item
except Exception as e:
self.logger.error(e)