class IfengSpider(scrapy.Spider):
name = "tech"
start_urls = [
"http://tech.ifeng.com/listpage/26344/1/list.shtml", #问题来了
"http://tech.ifeng.com/listpage/26333/1/list.shtml", #车科技
"http://tech.ifeng.com/listpage/26335/1/list.shtml", #可穿戴
"http://tech.ifeng.com/listpage/26334/1/list.shtml", #智慧家庭
"http://digi.ifeng.com/listpage/4085/1/list.shtml", #手机
"http://digi.ifeng.com/listpage/11143/1/list.shtml", #苹果
"http://digi.ifeng.com/listpage/11148/1/list.shtml", #平板
"http://digi.ifeng.com/listpage/2689/1/list.shtml", #笔记本
"http://digi.ifeng.com/listpage/5098/1/list.shtml", #影像
]
def parse(self, response):
# response.body
soup = BeautifulSoup(response.body, "lxml")
divs = soup.findAll('div', {'class': 'box_list clearfix'})
for div in divs:
# title, content,url
item = IfengItem()
h2 = div.find('h2')
link = h2.find('a')
url = link['href']
item['url'] = url
title = link['title']
item['title'] = title
response2 = urllib.urlopen(url)
soup2 = BeautifulSoup(response2, "lxml")
content = soup2.find('div', {'id': 'artical_real'}).get_text()
item['content'] = content
item['label'] = 'technology'
if self.check(item['url']):
yield item
# //*[@id="pagenext"] //*[@id="pagenext"]
next_url = response.xpath(
"//*[@id='pagenext'] /@href").extract() # 找到下一个链接，也就是翻页。
if next_url:
yield scrapy.Request(next_url[0], callback=self.parse)
def check(self, url):
self.database = Database()
self.database.connect('crawl_data')
sql = "SELECT * FROM news where url=%s order by url"
str_article_url = url.encode('utf-8')
data = (str_article_url, )
try:
search_result = self.database.query(sql, data)
if search_result == ():
self.database.close()
return True
except Exception, e:
print e
traceback.print_exc()
self.database.close()
return False
class IfengSpider(scrapy.Spider):
name = "cul"
start_urls = [
"http://culture.ifeng.com/listpage/59669/1/list.shtml", #眼界
"http://culture.ifeng.com/listpage/59668/1/list.shtml", #艺文
"http://culture.ifeng.com/listpage/59667/1/list.shtml", #思想
"http://culture.ifeng.com/listpage/59665/1/list.shtml", #文学
"http://culture.ifeng.com/listpage/59664/1/list.shtml", #热点
]
def parse(self, response):
# response.body
soup = BeautifulSoup(response.body, "lxml")
divs = soup.findAll('div', {'class': 'box_list clearfix'})
for div in divs:
# title, content,url
item = IfengItem()
h2 = div.find('h2')
link = h2.find('a')
url = link['href']
item['url'] = url
title = link['title']
item['title'] = title
response2 = urllib.urlopen(url)
soup2 = BeautifulSoup(response2, "lxml")
content = soup2.find('div', {'id': 'main_content'}).get_text()
item['content'] = content
item['label'] = 'culture'
if self.check(item['url']):
yield item
# //*[@id="pagenext"] //*[@id="pagenext"]
next_url = response.xpath(
"//*[@id='pagenext'] /@href").extract() # 找到下一个链接，也就是翻页。
if next_url:
yield scrapy.Request(next_url[0], callback=self.parse)
def check(self, url):
self.database = Database()
self.database.connect('crawl_data')
sql = "SELECT * FROM news where url=%s order by url"
str_article_url = url.encode('utf-8')
data = (str_article_url, )
try:
search_result = self.database.query(sql, data)
if search_result == ():
self.database.close()
return True
except Exception, e:
print e
traceback.print_exc()
self.database.close()
return False
class IfengSpider(scrapy.Spider):
name = "history1"
start_urls = [
"http://news.ifeng.com/listpage/71096/1/list.shtml", #假设历史
"http://news.ifeng.com/listpage/41708/1/list.shtml", #凤凰历史
"http://news.ifeng.com/listpage/70296/1/list.shtml", #兰台说史
]
def parse(self, response):
# response.body
soup = BeautifulSoup(response.body, "lxml")
#/html/body/div[4]/div[1]/div/div/div[1]/a
divs = soup.findAll('div', {'class': 'con_lis show'})
for div in divs:
# title, content,url
item = IfengItem()
url = div.find('a')['href']
title = div.find('h4').get_text()
item['url'] = url
item['title'] = title
response2 = urllib.urlopen(url)
soup2 = BeautifulSoup(response2, "lxml")
content = soup2.find('div', {'id': 'yc_con_txt'}).get_text()
item['content'] = content
item['label'] = 'history'
if self.check(item['url']):
yield item
#//*[@id="pagenext"]
next_url = response.xpath(
"//*[@id='pagenext'] /@href").extract() # 找到下一个链接，也就是翻页。
if next_url:
yield scrapy.Request(next_url[0], callback=self.parse)
def check(self, url):
self.database = Database()
self.database.connect('crawl_data')
sql = "SELECT * FROM news where url=%s order by url"
str_article_url = url.encode('utf-8')
data = (str_article_url, )
try:
search_result = self.database.query(sql, data)
if search_result == ():
self.database.close()
return True
except Exception, e:
print e
traceback.print_exc()
self.database.close()
return False
def check(self, url):
self.database = Database()
self.database.connect('crawl_data')
sql = "SELECT * FROM news where url=%s order by url"
str_article_url = url.encode('utf-8')
data = (str_article_url, )
try:
search_result = self.database.query(sql, data)
if search_result == ():
self.database.close()
return True
except Exception, e:
print e
traceback.print_exc()
class IfengSpider(scrapy.Spider):
name = "sports"
start_urls = [
"http://sports.ifeng.com/listpage/11244/1/list.shtml", #中国足球
"http://sports.ifeng.com/listpage/31190/1/list.shtml", #中超
"http://sports.ifeng.com/listpage/35586/1/list.shtml", #亚冠
"http://sports.ifeng.com/listpage/31186/1/list.shtml",#英超
"http://sports.ifeng.com/listpage/31188/1/list.shtml", #西甲
"http://sports.ifeng.com/listpage/31198/1/list.shtml",#欧冠
"http://sports.ifeng.com/listpage/31419/1/list.shtml",#田径
"http://sports.ifeng.com/listpage/31418/1/list.shtml",#网球
"http://sports.ifeng.com/listpage/34120/1/list.shtml",#排球
"http://sports.ifeng.com/listpage/11246/1/list.shtml",#国际足球
"http://sports.ifeng.com/listpage/31194/1/list.shtml",#CBA
"http://sports.ifeng.com/listpage/11247/1/list.shtml",#综合
]
def parse(self, response):
# response.body
soup = BeautifulSoup(response.body, "lxml")
divs = soup.findAll('div', {'class': 'box_list clearfix'})
for div in divs:
# title, content,url
item = IfengItem()
h2 = div.find('h2')
link = h2.find('a')
url = link['href']
item['url'] = url
title = link['title']
item['title'] = title
response2 = urllib.urlopen(url)
soup2 = BeautifulSoup(response2, "lxml")
content = soup2.find('div', {'id': 'artical_real'}).get_text()
item['content'] = content
item['label'] = 'sports'
if self.check(item['url']):
yield item
# //*[@id="pagenext"] //*[@id="pagenext"]
next_url = response.xpath("//*[@id='pagenext'] /@href").extract() # 找到下一个链接，也就是翻页。
if next_url:
yield scrapy.Request(next_url[0], callback=self.parse)
def check(self, url):
self.database = Database()
self.database.connect('crawl_data')
sql = "SELECT * FROM news where url=%s order by url"
str_article_url = url.encode('utf-8')
data = (str_article_url,)
try:
search_result = self.database.query(sql, data)
if search_result == ():
self.database.close()
return True
except Exception, e:
print e
traceback.print_exc()
self.database.close()
return False
class IfengSpider(scrapy.Spider):
name = "mil3"
start_urls = [
"http://news.qq.com/l/milite/milgn/list2010122872223.htm", #国内军情
"http://news.qq.com/l/milite/milhqj/list2010122872321.htm",#环球军情
"http://news.qq.com/l/milite/junbei/list2012095132410.htm",#军备动态
]
base = "http://news.qq.com/l/milite/junbei/list2012095132410_"#80.htm
for i in range(2,51):
url = base +str(i)+".htm"
start_urls.append(url)
base = "http://news.qq.com/l/milite/milhqj/list2010122872321_"#80.htm
for i in range(2,333):
url = base +str(i)+".htm"
start_urls.append(url)
base = "http://news.qq.com/l/milite/milgn/list2010122872223_"#80.htm
for i in range(2,335):
url = base +str(i)+".htm"
start_urls.append(url)
def parse(self, response):
# response.body
soup = BeautifulSoup(response.body, "lxml")
root = soup.find('div', {'class': 'leftList'})
lis = root.findAll('li')
for li in lis:
# title, content,url
item = IfengItem()
url = li.find('a')['href']
item['url'] = url
title = li.get_text()
item['title'] = title
response2 = urllib.urlopen(url)
soup2 = BeautifulSoup(response2, "lxml")
try:
content = soup2.find('div', {'id': 'Cnt-Main-Article-QQ'}).get_text()#Cnt-Main-Article-QQ
item['content'] = content
except AttributeError:
print AttributeError.message
item['label'] = 'military'
if self.check(item['url']):
yield item
# next_url = response.xpath("//*[@class='f12'] /@href").extract() # 找到下一个链接，也就是翻页。
#
# if next_url:
# yield scrapy.Request(next_url[0], callback=self.parse)
def check(self, url):
self.database = Database()
self.database.connect('crawl_data')
sql = "SELECT * FROM news where url=%s order by url"
str_article_url = url.encode('utf-8')
data = (str_article_url,)
try:
search_result = self.database.query(sql, data)
if search_result == ():
self.database.close()
return True
except Exception, e:
print e
traceback.print_exc()
self.database.close()
return False