def parse_baijiahao_contents(self, response):
# 从html中提取出所有的正文内容
content = response.xpath(
'/html/body/div[@id = "detail-page"]/div[@id="content-container"]',
encoding='UTF-8')
content = content.xpath('//span[@class="bjh-p"]/text()',
encoding="UTF-8").extract()
# 将正文的所有句子连接成字符串
content_string = ""
for item in content:
if item != "":
content_string += item.replace('\xa0', '').replace('\xa9', '')
# 去掉正文中的换行符和空格
content_string = content_string.replace('\n', "")
content_string = content_string.replace(" ", "")
content_string = content_string.replace("\u3000", "")
# 将获取到的字符串存入item中
item = MuseumNewsSpiderItem()
item['news_id'] = self.getNewsID(response.url)
item['main_content'] = content_string
self.id += 1
yield item
def parse(self, response):
news_body = response.xpath("//div[@class='content_czyd']")[0]
news_list = news_body.xpath(".//div[@class='list_list']")
for news in news_list:
title = news.xpath("./div/dt/a/text()")
time = news.xpath("./div/dt/span/text()")
content = news.xpath("./div/dd/a/text()")
href = news.xpath("./div/dt/a/@href")
if len(title) == 0 or len(time) == 0 or len(content) == 0 or len(
href) == 0:
continue
title = title[0].extract()
time = time[0].extract()
content = content[0].extract()
href = prefixURL + href[0].extract()
author = "北京鲁迅博物馆"
description = "1"
tag = 1
item = MuseumNewsSpiderItem()
item['title'] = title
item['author'] = author
item['time'] = time
item['description'] = description
item['content'] = content
item['url'] = href
item['tag'] = tag
yield item
print('page = {}'.format(self.page))
if self.page <= 6:
self.page += 1
new_url = URL.format(page=self.page)
print(new_url)
yield Request(new_url, callback=self.parse, dont_filter=True)
def parse(self, response):
news_body = response.xpath("//td[@height='450']")[0]
news_list = news_body.xpath(".//table[@width='85%']")
for news in news_list:
info = news.xpath(".//text()")
if len(info) == 0:
continue
title = info[1].extract()
time = info[0].extract().replace("\xa0", "")
content = title
href = prefixURL + news.xpath(".//@href")[0].extract()
author = "首都博物馆"
description = "1"
tag = 1
item = MuseumNewsSpiderItem()
item['title'] = title
item['author'] = author
item['time'] = time
item['description'] = description
item['content'] = content
item['url'] = href
item['tag'] = tag
yield item
print('page = {}'.format(self.page))
if self.page < 71:
self.page += 1
new_url = URL.format(page=self.page)
print(new_url)
yield Request(new_url, callback=self.parse, dont_filter=True)
def parse(self, response):
news_list = response.xpath('//div[@class="result"]')
# print(news_list)
if not news_list:
self.end = True
return
for news in news_list:
href = news.xpath('./h3[@class="c-title"]/a/@href').extract()
url = "".join(href).replace("\n", "").replace(" ", "")
title = news.xpath('./h3[@class="c-title"]/a/text()').extract()
title = "".join(title).replace("\n", "").replace(" ", "")
content = news.xpath(
'./div[@class="c-summary c-row "]/text()').extract()
content = "".join(content).replace("\n", "").replace(" ", "")
if content == "":
content = news.xpath(
'./div[@class="c-summary c-row "]/div[2]/text()').extract(
)
content = "".join(content).replace("\n", "").replace(" ", "")
author_time = news.xpath(
'./div[@class="c-summary c-row "]//p[@class="c-author"]/text()'
).extract()
author_time = "".join(author_time).replace("\n",
"").replace(" ",
"").split()
author = ""
time = ""
if author_time: # 有些新闻没有作者和时间
author = author_time[0]
s_time = author_time[1]
if s_time:
time = self.parse_time(s_time)
else:
time = s_time
description = "1"
tag = 1
item = MuseumNewsSpiderItem()
item['title'] = title
item['author'] = author
item['time'] = time
item['description'] = description
item['content'] = content
item['url'] = url
item['tag'] = tag
yield item
print('page = {}'.format(self.page))
if not self.end:
self.page += 1
new_url = URL.format(museum=self.museum,
bt=self.startTime,
et=self.endTime,
page=self.page * 10)
print(new_url)
yield Request(new_url, callback=self.parse, dont_filter=True)
def parse(self, response):
url = response.url
if "baijiahao" in url:
yield scrapy.Request(url, callback=self.parse_baijiahao_contents)
elif "new.qq.com" in url:
yield scrapy.Request(url, callback=self.parse_tencent_contents)
elif "news.ifeng.com" in url:
yield scrapy.Request(url, callback=self.parse_ifeng_contents)
elif "news.163.com" in url:
yield scrapy.Request(url, callback=self.parse_163_news_contents)
elif "3g.163.com" in url:
yield scrapy.Request(url, callback=self.parse_3g_163_contents)
elif "thepaper.cn" in url:
yield scrapy.Request(url, callback=self.parse_pengpai_contents)
elif "news.sina.com.cn" in url:
yield scrapy.Request(url, callback=self.parse_sina_contents)
elif "paper.people.com.cn" in url:
yield scrapy.Request(url,
callback=self.parse_paper_people_contents)
elif "xinhuanet.com" in url:
yield scrapy.Request(url, callback=self.parse_xinhuanet_contents)
elif "bmnh.org.cn" in url:
yield scrapy.Request(url, callback=self.parse_bmnh_contents)
elif "capitalmuseum" in url:
yield scrapy.Request(url,
callback=self.parse_capital_museum_contents)
elif "cstm.cdstm.cn" in url:
yield scrapy.Request(url, callback=self.parse_cstm_contents)
elif "luxunmuseum" in url:
yield scrapy.Request(url, callback=self.parse_luxunmuseum_contents)
elif "jb.mil.cn" in url:
yield scrapy.Request(url,
callback=self.parse_military_museum_contents)
elif "gmc" in url:
yield scrapy.Request(url, callback=self.parse_gmc_contents)
else:
item = MuseumNewsSpiderItem()
cursor = self.mydatabase.cursor()
sql = "select content from new where url='{}'".format(url)
cursor.execute(sql)
result = cursor.fetchone()
cursor.close()
id = self.getNewsID(url)
if id != []:
item['news_id'] = id
else:
item['news_id'] = -1
item['main_content'] = result[0]
yield item
def parse_xinhuanet_contents(self, response):
content = response.xpath('//div[@id="p-detail"]', encoding="UTF-8")
content = content.xpath('//p/text()').extract()
content_string = ""
for item in content:
if item != "":
content_string += item.replace('\xa0', '').replace('\xa9', '')
content_string = content_string.replace('\n', "")
content_string = content_string.replace(" ", "")
content_string = content_string.replace("\u3000", "")
item = MuseumNewsSpiderItem()
item['news_id'] = self.getNewsID(response.url)
item['main_content'] = content_string
yield item
def parse_tencent_contents(self, response):
content = response.xpath('/html/body', encoding="UTF-8")
content = content.xpath('//p[@class="one-p"]/text()').extract()
content_string = ""
for item in content:
if item != "":
content_string += item.replace('\xa0', '').replace('\xa9', '')
content_string = content_string.replace('\n', "")
content_string = content_string.replace(" ", "")
content_string = content_string.replace("\u3000", "")
item = MuseumNewsSpiderItem()
item['news_id'] = self.getNewsID(response.url)
item['main_content'] = content_string
yield item
def parse_gmc_contents(self, response):
content = response.xpath('//div[@class="article-cont"]')
content = content.xpath('//p/span/text()').extract()
content_string = ""
for item in content:
if item != "":
content_string += item.replace('\xa0', '').replace('\xa9', '')
content_string = content_string.replace('\n', "")
content_string = content_string.replace(" ", "")
content_string = content_string.replace("\u3000", "")
content_string = content_string.replace("\xa0", "").replace("\r", "")
item = MuseumNewsSpiderItem()
item['news_id'] = self.getNewsID(response.url)
item['main_content'] = content_string
yield item
def parse_capital_museum_contents(self, response):
content = response.xpath("//span[@class='wcontent']")
content = content.xpath("//p/text()").extract()
content_string = ""
for item in content:
if item != "":
content_string += item.replace('\xa0', '').replace('\xa9', '')
content_string = content_string.replace('\n', "")
content_string = content_string.replace(" ", "")
content_string = content_string.replace("\u3000", "")
content_string = content_string.replace("\xa0", "").replace("\r", "")
item = MuseumNewsSpiderItem()
item['news_id'] = self.getNewsID(response.url)
item['main_content'] = content_string
yield item
def parse_ifeng_contents(self, response):
content = response.xpath("//div[@class='text-3zQ3cZD4']",
encoding="UTF-8")
content = content.xpath("//p/text()").extract()
content_string = ""
for item in content:
if item != "":
content_string += item.replace('\xa0', '').replace('\xa9', '')
content_string = content_string.replace('\n', "")
content_string = content_string.replace(" ", "")
content_string = content_string.replace("\u3000", "")
item = MuseumNewsSpiderItem()
item['news_id'] = self.getNewsID(response.url)
item['main_content'] = content_string
yield item
def parse_pengpai_contents(self, response):
content = response.xpath(
'//*[@id="root"]/div/div[3]/div[1]/div[1]/div[3]/div/div[1]',
encoding="UTF-8")
content = content[0].xpath('//p/text()').extract()
content_string = ""
for item in content:
if item != "":
content_string += item.replace('\xa0', '').replace('\xa9', '')
content_string = content_string.replace('\n', "")
content_string = content_string.replace(" ", "")
content_string = content_string.replace("\u3000", "")
item = MuseumNewsSpiderItem()
item['news_id'] = self.getNewsID(response.url)
item['main_content'] = content_string
yield item
def parse_bmnh_contents(self, response):
content = response.xpath(
'//div[@class="content_singler"]/div[@class="single_block"]',
encoding="UTF-8")
content = content.xpath('//p')
content = content.xpath('//span/text()').extract()
content_string = ""
for item in content:
if item != "":
content_string += item.replace('\xa0', '').replace('\xa9', '')
content_string = content_string.replace('\n', "")
content_string = content_string.replace(" ", "")
content_string = content_string.replace("\u3000", "")
item = MuseumNewsSpiderItem()
item['news_id'] = self.getNewsID(response.url)
item['main_content'] = content_string
yield item
