class SancunSpider(scrapy.Spider):
name = 'tsxsy_bbsgx'
allowed_domains = ['www.bbsgx.com']
#start_urls = ['http://www.xbiquge.la/10/10489/']
url_ori = "http://www.bbsgx.com"
url_firstchapter = "http://www.bbsgx.com/book_211549/65039517.html"
name_txt = "./novels/贴身小神医bbsgx"
pipeline = XbiqugePipeline()
pipeline.createtable(name)
item = XbiqugeItem()
item['name'] = name
item['url_firstchapter'] = url_firstchapter
item['name_txt'] = name_txt
def start_requests(self):
start_urls = ['http://www.bbsgx.com/book_211549/']
for url in start_urls:
yield scrapy.Request(url=url, callback=self.parse)
def parse(self, response):
dl = response.css('#list dl dd') #提取章节链接相关信息
for dd in dl:
self.url_c = self.url_ori + '/book_211549/' + dd.css(
'a::attr(href)').extract()[0] #组合形成小说的各章节链接
#print(self.url_c)
#yield scrapy.Request(self.url_c, callback=self.parse_c,dont_filter=True)
yield scrapy.Request(
self.url_c, callback=self.parse_c
) #以生成器模式（yield）调用parse_c方法获得各章节链接、上一页链接、下一页链接和章节内容信息。
#print(self.url_c)
def parse_c(self, response):
#item = XbiqugeItem()
#item['name'] = self.name
#item['url_firstchapter'] = self.url_firstchapter
#item['name_txt'] = self.name_txt
self.item['url'] = response.url
self.item['preview_page'] = self.url_ori + response.css(
'#wrapper > div.content_read > div > div.bookname > div.bottem1 > a:nth-child(2)::attr(href)'
).extract()[0]
self.item['next_page'] = self.url_ori + response.css(
'#wrapper > div.content_read > div > div.bookname > div.bottem1 > a:nth-child(4)::attr(href)'
).extract()[0]
title = response.css(
'#wrapper > div.content_read > div > div.bookname > h1::text'
).extract()[0]
contents = response.css('#content::text').extract()
text = ''
for content in contents:
text = text + content
#print(text)
self.item['content'] = title + "\n" + text.replace(
'\15', '\n') #各章节标题和内容组合成content数据，\15是^M的八进制表示，需要替换为换行符。
yield self.item #以生成器模式（yield）输出Item对象的内容给pipelines模块。
if self.item['url'][33:41] == self.item['next_page'][33:41]:
self.url_c = self.item['next_page']
yield scrapy.Request(self.url_c, callback=self.parse_c)
class SancunSpider(scrapy.Spider):
name = 'kjtsg'
allowed_domains = ['www.xbiquge.la']
#start_urls = ['http://www.xbiquge.la/10/10489/']
url_ori = "http://www.xbiquge.la"
url_firstchapter = "http://www.xbiquge.la/15/15480/8186557.html"
name_txt = "./novels/科技图书馆"
pipeline = XbiqugePipeline()
pipeline.clearcollection(
name) #清空小说的数据集合（collection），mongodb的collection相当于mysql的数据表table
item = XbiqugeItem()
item['id'] = 0 #新增id字段，便于查询
item['name'] = name
item['url_firstchapter'] = url_firstchapter
item['name_txt'] = name_txt
def start_requests(self):
start_urls = ['http://www.xbiquge.la/15/15480/']
for url in start_urls:
yield scrapy.Request(url=url, callback=self.parse)
def parse(self, response):
dl = response.css('#list dl dd') #提取章节链接相关信息
for dd in dl:
self.url_c = self.url_ori + dd.css('a::attr(href)').extract()[
0] #组合形成小说的各章节链接
#print(self.url_c)
#yield scrapy.Request(self.url_c, callback=self.parse_c,dont_filter=True)
yield scrapy.Request(
self.url_c, callback=self.parse_c
) #以生成器模式（yield）调用parse_c方法获得各章节链接、上一页链接、下一页链接和章节内容信息。
#print(self.url_c)
def parse_c(self, response):
#item = XbiqugeItem()
#item['name'] = self.name
#item['url_firstchapter'] = self.url_firstchapter
#item['name_txt'] = self.name_txt
self.item['id'] += 1
self.item['url'] = response.url
self.item['preview_page'] = self.url_ori + response.css(
'div .bottem1 a::attr(href)').extract()[1]
self.item['next_page'] = self.url_ori + response.css(
'div .bottem1 a::attr(href)').extract()[3]
title = response.css('.con_top::text').extract()[4]
contents = response.css('#content::text').extract()
text = ''
for content in contents:
text = text + content
#print(text)
self.item['content'] = title + "\n" + text.replace(
'\15', '\n') #各章节标题和内容组合成content数据，\15是^M的八进制表示，需要替换为换行符。
yield self.item #以生成器模式（yield）输出Item对象的内容给pipelines模块。
def parse_c(self, response):
item = XbiqugeItem()
item['url'] = response.url
item['preview_page'] = "http://www.xbiquge.la" + response.css('div .bottem1 a::attr(href)').extract()[1]
item['next_page'] = "http://www.xbiquge.la" + response.css('div .bottem1 a::attr(href)').extract()[3]
title = response.css('.con_top::text').extract()[4]
contents = response.css('#content::text').extract()
text=''
for content in contents:
text = text + content
#print(text)
item['content'] = title + "\n" + text.replace('\15', '\n') #各章节标题和内容组合成content数据，\15是^M的八进制表示，需要替换为换行符。
yield item #以生成器模式（yield）输出Item对象的内容给pipelines模块。
def parse_c(self, response):
item = XbiqugeItem()
item['url'] = response.url
item['preview_page'] = "http://www.778buy.com/659_659168/" + response.css('#bgdiv > table.border_l_r > tbody > tr:nth-child(2) > td > a:nth-child(1)::attr(href)').extract()[0]
item['next_page'] = "http://www.778buy.com/659_659168/"+ response.css('#bgdiv > table.border_l_r > tbody > tr:nth-child(2) > td > a:nth-child(3)::attr(href)').extract()[0]
title = response.css('#bgdiv > table.border_l_r > tbody > tr:nth-child(1) > td > div > h1::text').extract()[0]
contents = response.css('div #content::text').extract()
text=''
for content in contents:
text = text + content
#print(text)
item['content'] = title + "\n" + text.replace('\15', '\n') #各章节标题和内容组合成content数据，\15是^M的八进制表示，需要替换为换行符。
yield item #以生成器模式（yield）输出Item对象的内容给pipelines模块。
def parse_c(self, response):
item = XbiqugeItem()
item['url'] = response.url
item['preview_page'] = "https://www.86zw.cc" + response.css('div.main_content div#nr_content.nr_content div.nr_page a::attr(href)').extract()[0]
item['next_page'] = "https://www.86zw.cc" + response.css('div.main_content div#nr_content.nr_content div.nr_page a::attr(href)').extract()[3]
title = response.css('div.main_content div#nr_content.nr_content div.nr_title h3::text').extract()[0]
contents = response.css('div.main_content div#nr_content.nr_content div.novelcontent p#articlecontent.articlecontent::text').extract()
text=''
for content in contents:
text = text + content
#print(text)
item['content'] = title + "\n" + text.replace('\15', '\n') #各章节标题和内容组合成content数据，\15是^M的八进制表示，需要替换为换行符。
yield item #以生成器模式（yield）输出Item对象的内容给pipelines模块。
class SancunSpider(scrapy.Spider):
name = 'sancun'
allowed_domains = ['www.xbiquge.la']
#start_urls = ['http://www.xbiquge.la/10/10489/']
url_ori = "https://www.xbiquge.la"
url_firstchapter = "https://www.xbiquge.la/10/10489/4534454.html"
name_txt = "./novels/三寸人间"
url_chapters = url_firstchapter[0:32]
pipeline = XbiqugePipeline()
novelcollection = pipeline.get_collection(
name) #获取小说数据集cursor对象，mongodb的数据集（collection）相当于mysql的数据表table
#--------------------------------------------
#如果next_page的值是小说目录页面url，则把包含目录页面的记录删除，以免再次抓取时，出现多>个目录页面url，使得无法获得最新内容。
if novelcollection.find({"next_page": url_chapters}).count() != 0:
print(
"包含目录页面url的记录:",
novelcollection.find({
"next_page": url_chapters
}, {
"_id": 0,
"id": 1,
"url": 1,
"next_page": 1
}).next())
novelcollection.remove({"next_page": url_chapters})
print("已删除包含目录页面url的记录。")
#--------------------------------------------
novelcounts = novelcollection.find().count()
novelurls = novelcollection.find({}, {"_id": 0, "id": 1, "url": 1})
item = XbiqugeItem()
item['id'] = novelcounts #id置初值为colletion的记录总数
item['name'] = name
item['url_firstchapter'] = url_firstchapter
item['name_txt'] = name_txt
def start_requests(self):
start_urls = [self.url_chapters]
print("小说目录url:", start_urls)
for url in start_urls:
yield scrapy.Request(url=url, callback=self.parse)
def parse(self, response): #网页提取数据，并与mongodb数据集比较，没有相同的数据才从网页抓取。
f = open("/root/xbiquge_w/url_list.txt", "w") #打开文件，以便写入抓取页面url
count_bingo = 0 #数据集中已有记录的条数
dl = response.css('#list dl dd') #提取章节链接相关信息
for dd in dl:
count_iterator = 0
self.url_c = self.url_ori + dd.css('a::attr(href)').extract()[
0] #组合形成小说的各章节链接
#print("网页提取url:", self.url_c)
self.novelurls = self.novelcollection.find({}, {
"_id": 0,
"id": 1,
"url": 1
}) #通过重新赋值迭代器来重置迭代器指针，使for循环能够从头遍历迭代器。
for url in self.novelurls:
#print("mongodb提取url:", url)
if url["url"] == self.url_c: #如果数据集中找到与网页提取的url值相同，则跳出循环
count_bingo += 1
count_iterator += 1
break
if count_iterator != 0: #如果有命中结果，则继续下一个循环，不执行爬取动作
continue
#print("爬取url:",self.url_c)
f.write("爬取url:" + self.url_c + "\n")
#yield scrapy.Request(self.url_c, callback=self.parse_c,dont_filter=True)
yield scrapy.Request(
self.url_c, callback=self.parse_c
) #以生成器模式（yield）调用parse_c方法获得各章节链接、上一页链接、下一页链接和章节内容信息。
#print(self.url_c)
f.close()
print("数据集已有记录数count_bingo:", count_bingo)
def parse_c(self, response):
self.item['id'] += 1
self.item['url'] = response.url
self.item['preview_page'] = self.url_ori + response.css(
'div .bottem1 a::attr(href)').extract()[1]
self.item['next_page'] = self.url_ori + response.css(
'div .bottem1 a::attr(href)').extract()[3]
title = response.css('.con_top::text').extract()[4]
contents = response.css('#content::text').extract()
text = ''
for content in contents:
text = text + content
#print(text)
self.item['content'] = title + "\n" + text.replace(
'\15', '\n') #各章节标题和内容组合成content数据，\15是^M的八进制表示，需要替换为换行符。
yield self.item #以生成器模式（yield）输出Item对象的内容给pipelines模块。
if self.item['url'][32:39] == self.item['next_page'][
32:39]: #同一章有分页的处理
self.url_c = self.item['next_page']
yield scrapy.Request(self.url_c, callback=self.parse_c)