def parse_item(self, response):
item = MangaItem()
item['name'] = response.css("h1.titre-big").xpath('./text()').extract()
item['release_date'] = response.css("div.date_sortie").xpath('./text()').extract()
item['collection'] = response.css("div.categorie").xpath('./text()').extract()
item['cover'] = response.css("div.item-fiche-livre div.mediao__figure img").xpath('./@src').extract()
item['tome'] = response.css("div.block_infos_techniques div:nth-child(2)").xpath('./text()').extract()
yield item
def parse_image_page(self, response):
srcs = response.xpath(self.xpath.get("image")).extract()
self.log(srcs)
title = response.xpath("//title/text()").extract_first().split("-")
manga_name = title[0].split(" ")[0]
chapter_name = title[1].strip()
logging.info("downloading " + manga_name + ": " + chapter_name)
item = MangaItem(image_urls=srcs, manga_name=manga_name, chapter_name=chapter_name)
return item
def parsePage(self, response):
item = MangaItem()
item['book'] = response.meta['book']
item['page'] = response.css(".navigation .button-success::text").get()
item['src'] = 'http://p17.manhuapan.com/' + response.css('script').re(r'mhurl="(.*?)"')[0]
yield item
if '下一页' == response.css('.navigation .pure-button.pure-button-primary::text').getall()[-1]:
next_url = response.css('.navigation .pure-button.pure-button-primary::attr("href")').getall()[-1]
request = Request(response.meta['url'] + next_url, self.parsePage)
request.meta['book'] = response.meta['book']
request.meta['url'] = response.meta['url']
yield request
def parse_image_page(self, response):
srcs = response.xpath(self.xpath.get("image")).extract()
self.log(srcs)
manga_name = response.xpath("//h1/text()").extract_first()
# chapter_name = title[1].strip()
logging.info("downloading " + manga_name)
item = MangaItem(image_urls=srcs, manga_name=manga_name, chapter_name="")
# item["image_urls"] = srcs
# item["chapter_name"] = chapter_name
# item["manga_name"] = manga_name
return item
def parse_item(self, response):
item = MangaItem()
manga_attr = response.xpath("//table/tr/td")
if len(manga_attr) == 0:
return []
item['tags'] = []
#title
item['title'] = response.css(".odd_anim_title_m").xpath(
".//h1/text()").extract()
#synonym
item['synonym'] = manga_attr[0].xpath("./text()").extract()
#og name
item['og_name'] = manga_attr[1].xpath("./text()").extract()
#author url
item['author_url'] = manga_attr[2].xpath('./a/@href').extract()
#author
item['author'] = manga_attr[2].xpath("./a/text()").extract()
#area tag
item['tags'] += manga_attr[3].xpath("./a/text()").extract()
#status tag
item['tags'] += manga_attr[4].xpath("./a/text()").extract()
#hits
item['hits'] = manga_attr[5].xpath("./a/text()").extract()
#type tag
item['tags'] += manga_attr[6].xpath("./a/text()").extract()
#category tag
item['tags'] += manga_attr[7].xpath("./a/text()").extract()
#cover
item['cover'] = response.css(
"div.anim_intro_ptext > a > img::attr(src)").extract()
urls = response.css(
"div.cartoon_online_border > ul > li > a::attr(href)").extract()
nums = range(1, len(urls) + 1)
item['chapters'] = dict(zip(nums, urls))
id_text = response.xpath("//script")[4].extract()
m = re.search(r"\"([0-9]+)\"", id_text)
if m:
id = m.group(1)
req = Request(url="http://manhua.dmzj.com/hits/" + id + ".json",
callback=self.parse_item2)
req.meta["item"] = item
return req
else:
return item