def parse(self, response):
i = 0
for item in response.xpath("/html/body/div[2]/div[2]/ul/li/a"):
i = i+1
movClass = item.xpath("text()").extract()
movUrl = item.xpath("@href").extract_first()
oneItem = ExampleItem()
oneItem['movClass'] = movClass
oneItem['movUrl'] = movUrl
for j in range(1,2):
if j==1:
mvUrl2 = movUrl+str('index.html')
else:
mvUrl2 = movUrl+str('index_%s.html'%j)
try:
# print("++++++++++"+mvUrl2)
# yield oneItem
# yield scrapy.Request(url=mvUrl2,callback=lambda response,mvclass=movClass: self.parse_url(response,mvclass))
yield scrapy.Request(url=mvUrl2,callback=self.parse_url())
except Exception as error:
print("-------------")
print(error)
pass
except RuntimeError as error:
print("******************")
print(error)
if i>2:
break
def parse_item(self, response):
item = ExampleItem()
item['name'] = response.css(
'tr#places_country__row td.w2p_fw::text').extract()
item['population'] = response.css(
'tr#places_population__row td.w2p_fw::text').extract()
return item
def parse_directory(self, response):
item = ExampleItem()
url = response.url
jid = self.md5(url)
title = response.xpath(r'//h1/text()').extract()[0]
location = response.xpath(
r'//div/span[@class="lname"]/text()').extract()[0]
exp = response.xpath(
r'//div[@class="t1"]/span[1]/text()').extract()[0].strip('年经验')
if '无工作' in exp:
exp = 0
else:
exp = exp.strip('-')[0]
degree = response.xpath(
r'//div[@class="t1"]/span[2]/text()').extract()[0]
crawled = datetime.datetime.now().strftime('%Y-%m-%d')
money = response.xpath(r'//div[@class="cn"]/strong/text()').extract()
maxmoney = minmoney = 0
if money:
money = money[0]
else:
pass
if '/月' in money:
money = money.strip('/月')
money = money.split('-')
if 'k' in money[1]:
maxmoney = float(money[1].strip('k')) * 1000
minmoney = float(money[0]) * 1000
elif '千' in money[1]:
maxmoney = float(money[1].strip('千')) * 1000
minmoney = float(money[0]) * 1000
elif '万' in money[1]:
maxmoney = float(money[1].strip('万')) * 10000
minmoney = float(money[0]) * 10000
elif '万/年' in money:
money = money.strip('/年')
money = money.split('-')
if '万' in money[1]:
maxmoney = float(money[1].strip('万')) * 1000
minmoney = float(money[0]) * 1000
elif '以上' in money:
minmoney = maxmoney = money.strip('元/月以上')
elif '面议' in money:
minmoney = maxmoney = 0
elif '以下' in money:
minmoney = maxmoney = int(money.strip('元/月以下'))
item['title'] = title
item['maxmoney'] = int(maxmoney)
item['minmoney'] = int(minmoney)
item['crawled'] = crawled
item['location'] = location
item['exp'] = exp
item['degree'] = degree
item['url'] = url
item['jid'] = jid
print(title, location, exp, degree, url)
yield item
def parse(self, response):
hxs = HtmlXPathSelector(response)
titles = hxs.select("//p")
items = []
for titles in titles:
item = ExampleItem()
item['year'] = titles.select("span/text()").extract()[0]
item['title'] = titles.select("a/b/text()").extract()[0]
yield item
def parse(self, response):
print "s%d" % self.count,
self.count += 1
news_item = ExampleItem()
items = response.xpath("//div[@id='list']/a")
for item in items:
news_item["news_link"] = item.xpath("@href").extract()[0]
news_item["news_title"] = item.xpath("span/text()").extract()[0]
news_item["news_time"] = item.xpath("font/text()").extract()[0]
yield news_item
def parse_item(self, response):
item = ExampleItem()
name_css = 'tr#places_country__row td.w2p_fw::text'
item['name'] = response.css(name_css).extract()
pop_css = 'tr#places_population__row td.w2p_fw::text'
item['population'] = response.css(pop_css).extract()
#i['domain_id'] = response.xpath('//input[@id="sid"]/@value').extract()
#i['name'] = response.xpath('//div[@id="name"]').extract()
#i['description'] = response.xpath('//div[@id="description"]').extract()
return item
def parse_book(self, response):
book = ExampleItem()
table = response.xpath('//article/table')
book['name'] = response.xpath('//article//h1/text()').extract_first()
book['price'] = table.xpath('//tr[3]/td/text()').extract_first()
book['availability'] = table.xpath('//tr[6]/td/text()').re_first(
'(\d+)')
book['review_num'] = table.xpath('//tr[7]/td/text()').extract_first()
yield book
def parse(self, response):
item = ExampleItem()
for box in response.xpath(
'//div[dl[@class="f-list-item-wrap f-clear"]]'):
#获取每个div中的课程路径
item['url'] = box.xpath('./a[@title]/text()')
#获取div中的课程标题
#item['title'] = box.xpath('.//a[@class="js-title value title-font"]/text()').extract()[0].strip()
#获取div中的价格
#item['price'] = box.xpath('//div[1]/span[1]/text()')
yield item
def parseJobDetail(self, response):
print(response.status)
item = ExampleItem()
# 目标数据：职位名称、工作地点、职位类别、工作职责、工作要求
item['jobName'] = response.xpath('//td[@id="sharetitle"]/text()').extract()[0]
item['workLocation'] = response.xpath('//tr[@class="c bottomline"]/td[1]/text()').extract()[0]
item['jobType'] = response.xpath('//tr[@class="c bottomline"]/td[2]/text()').extract()[0]
item['jobDesc'] = response.xpath('//table[@class="tablelist textl"]/tr[3]//li/text()').extract()
item['jobInfo'] = response.xpath('//table[@class="tablelist textl"]/tr[4]//li/text()').extract()
# print(jobName,workLocation,jobType,jobDesc,jobInfo)
yield item
def parse(self, response):
print 'c%d' % self.count,
self.count += 1
news_item = ExampleItem()
items = response.xpath("//ul[@class='news-list']/li")
for item in items:
news_item["news_link"] = item.xpath("a/@href").extract()[0]
news_item["news_title"] = item.xpath("a/text()").extract()[0]
news_item["news_time"] = item.xpath(
"span[@class='time']/text()").extract()[0]
yield news_item
def parse_directory(self, response):
print(response.status)
list = response.xpath('//div[@class="post floated-thumb"]')
for node in list:
item = ExampleItem()
item['name'] = node.xpath('//div[@class="post-thumb"]/a/@title').extract_first()
item['url'] = node.xpath('//div[@class="post-thumb"]/a/@href').extract_first()
yield item
def parse_blog(self, response):
hxs = HtmlXPathSelector(response)
item = ExampleItem()
item['title'] = hxs.select(
"//div[@class='span9']/h1/a/text()").extract()
item['description'] = hxs.select(
"//div[@class='span9']/p[@class='lead']/text()").extract()
item['date'] = hxs.select(
"//div[@class='span9']/h1/small/text()").extract()
item['post'] = hxs.select("//div[@class='span9']/p/text()").extract()
return item
def parse_directory(self, response):
item = ExampleItem()
url = response.url
jid = self.md5(url)
title = response.xpath('//h1/text()').extract()[0]
money = response.xpath(
'//ul[@class="clearfix pos-relat"]/li[2]/em/text()').extract()[0]
minmoney = maxmoney = 0
if '-' in money:
money = money.split('-')
minmoney = int(money[0])
maxmoney = int(money[1].strip('元'))
elif '面议' in money:
pass
elif '元以上' in money:
minmoney = maxmoney = money.strip('元以上')
elif '元以下' in money:
minmoney = maxmoney = int(money.strip('元以下'))
degree = response.xpath(
'//ul[@class="clearfix pos-relat"]/li[3]/em/text()').extract()[0]
location = response.xpath(
'//ul[@class="clearfix pos-relat"]/li[8]/em/text()|//ul[@class="clearfix pos-relat"]/li[7]/em/text()'
).extract()[0].strip(' ')
# if location:
# location = location
# else:
# location = response.xpath('//ul[@class="clearfix pos-relat"]/li[7]/em/text()').extract()[0]
crawled = response.xpath('//p[@class="data-sty mb-5"]/span[1]/text()'
).extract()[0].strip('更新时间：')
crawled = self.Strfdate(crawled)
exp = response.xpath(
'//ul[@class="clearfix pos-relat"]/li[4]/em/text()').extract()[0]
p = re.compile(r'(\d+)')
exp = p.search(exp)
if exp:
exp = exp.group(1)
else:
exp = 0
# item['item'] =money
item["title"] = title
item["maxmoney"] = maxmoney
item["minmoney"] = minmoney
item["location"] = location
item["crawled"] = crawled
item["exp"] = exp
item["degree"] = degree
item["url"] = url
item["jid"] = jid
yield item
def parse(self, response):
sel = Selector(response)
sites = sel.xpath('/html/body/div[4]/div/div[2]/div[1]/ul/li')
#url = 'http://www.hbnu.edu.cn/'
item = ExampleItem()
url = []
item['title'] = '一级链接'
for site in sites:
item['url'] = site.xpath('a/@href').extract()
url.append(item)
yield (item)
#print(url[2]['url'])
yield scrapy.Request(url[2]['url'][0], callback=self.next)
def parse_directory(self, response):
item = ExampleItem()
url = response.url
jid = self.md5(url)
location = response.xpath(
'//div[@class="pos-area"]/span/span[1]/text()').extract()[0]
exp = response.xpath(
'//div[@class="pos_base_condition"]/span[3]/text()').extract()[0]
p = re.compile(r'(\d+)')
exp = p.search(exp)
if exp:
exp = exp.group(1)
else:
exp = 0
date_pub = response.xpath(
'//span[@class="pos_base_num pos_base_update"]/span/text()'
).extract()[0]
crawled = self.Strfdate(date_pub)
degree = response.xpath(
'//span[@class="item_condition"]/text()').extract()[0]
title = response.xpath(
'//div[@class="pos_base_info"]/span[1]/text()').extract()[0]
money = response.xpath('//div[@class="pos_base_info"]/span[2]/text()'
).extract()[0].strip('元/月\xa0')
minmoney = maxmoney = 0
if '-' in money:
money = money.split('-')
minmoney = int(money[0])
maxmoney = int(money[1])
elif '面议' in money:
pass
elif '以上' in money:
minmoney = maxmoney = money.strip('元/月以上')
elif '以下' in money:
minmoney = maxmoney = int(money.strip('元/月以下'))
item['url'] = url
item['jid'] = jid
item['title'] = title
item['location'] = location
item['exp'] = exp
item['degree'] = degree
item['maxmoney'] = maxmoney
item['minmoney'] = minmoney
item['crawled'] = crawled
yield item
def parse(self, response):
l = ExampleItem()
# Judge whether it's a not html file
if self.isNoHtmlFile(response) is True:
# Treat it like not html
self.saveItToFile(self.debug_nohtml_cache_dir, response)
else:
# Treat it like html
# According to the rules to judge whether it has the keywords, then save the file in directory
if self.htmlParseRulesSelector(response) is True:
self.saveItToFile(self.debug_dir, response)
l['name'] = response.css('title::text').get()
self.get_urls_store_redis(response)
l['url'] = response.url
yield l
def parse(self, response):
item = ExampleItem()
item['name'] = response.xpath(
'//article[@class="product_pod"]/h3/a/text()').extract()
print(item['name'])
item['price'] = response.xpath(
'//div[@class="product_price"]/p[@class="price_color"]/text()'
).extract()
print(item['price'])
#提取完数据后返回item
yield item
for i in range(1, 50):
url = 'http://books.toscrape.com/catalogue/page-' + str(
i) + '.html'
yield Request(url, callback=self.parse)
def parse_directory(self, response):
item = ExampleItem()
url = response.url
jid = self.md5(url)
# jid = re.compile(r'https://www.lagou.com/jobs/(\d+)')
# jid = jid.search(url)
# if jid :
# jid = jid.group(1)
location = response.xpath('//dd[@class="job_request"]/p/span[2]/text()'
).extract()[0].strip('/').strip(' /')
exp = response.xpath('//dd[@class="job_request"]/p/span[3]/text()'
).extract()[0].strip(' /').strip('经验')
if '年' in exp:
exp = exp.strip('年').strip('-')[0]
else:
exp = 0
degree = response.xpath('//dd[@class="job_request"]/p/span[4]/text()'
).extract()[0].strip(' /')
crawled = datetime.datetime.now().strftime('%Y-%m-%d')
title = response.xpath('//span[@class="name"]/text()').extract()[0]
money = response.xpath('//dd[@class="job_request"]/p/span[1]/text()'
).extract()[0].split('-')
maxmoney = minmoney = 0
if money:
money = money
else:
pass
if 'k' in money[0]:
minmoney = int(money[0].strip('k')) * 1000
maxmoney = int(money[1].strip('k ')) * 1000
# 加载数据
item['url'] = url
item['jid'] = jid
item['title'] = title
item['location'] = location
item['exp'] = exp
item['degree'] = degree
item['maxmoney'] = maxmoney
item['minmoney'] = minmoney
# item['money'] = money
item['crawled'] = crawled
yield item
def parse_directory(self, response):
node_all = response.xpath('//ul[@class="boxbdnopd"]/li')
for node in node_all:
item = ExampleItem()
name = node.xpath('.//h4/a/text()').extract()[0]
link = node.xpath('.//h4/a/@href').extract()[0]
description = node.xpath(
'.//p[@class="description"]/text()').extract()[0]
item["name"] = name
item["link"] = link
item["description"] = description
print("link==", link)
yield item
def parse(self, response):
list = response.xpath('//div[@class="post floated-thumb"]')
for node in list:
item = ExampleItem()
item['name'] = node.xpath(
'.//div[@class="post-thumb"]/a/@title').extract_first()
item['detailurl'] = node.xpath(
'.//div[@class="post-thumb"]/a/@href').extract_first()
yield item
#取到当前页面下其他页面的ｕｒｌ
next_urls = response.xpath(
'//a[@class="page-numbers"]/@href').extract()
print(next_urls)
for url in next_urls:
yield Request(url=url, callback=self.parse)
def parse(self, response):
with open('data.json', 'wb') as f:
f.write(response.body)
item = ExampleItem()
'''print('aaaaaa')
item['next_page'] = response.css('div.pageBox')[1].xpath('.//a[@class="next"]/@href').extract_first()'''
yield item
for box in response.xpath(
'//div[@class="f-list-item ershoufang-list"]'):
#获取每个div中的课程路径
#item['url'] = box.xpath('./@href')
#//*[@id="puid-2998490926"]/dl/dd[1]/a
#获取div中的课程标题
item['title'] = box.xpath(
'.//dd[@class="dd-item title"]/a[@class="js-title value title-font"]/text()'
).extract()[0]
#获取div中的价格
item['price'] = box.xpath(
'.//dd[@class="dd-item info"]/div[@class="price"]/span[@class="num"]/text()'
).extract()[0]
#获取房屋面积
item['area'] = box.xpath(
'.//dl[@class="f-list-item-wrap f-clear"]/dd[@class="dd-item size"]/span[5]/text()'
).extract()[0]
#房屋租赁方式
item['rent'] = box.xpath(
'.//dl[@class="f-list-item-wrap f-clear"]/dd[@class="dd-item size"]/span[@class="first js-huxing"]/text()'
).extract()[0]
yield item
next_page = 'http://bj.ganji.com' + response.css('div.pageBox')[
1].xpath('.//a[@class="next"]/@href').extract_first()
#print(next_page)
if next_page is not None:
next_page = response.urljoin(next_page)
yield scrapy.Request(next_page,
callback=self.parse,
headers={'referer': next_page})
def parse_directory(self, response):
item = ExampleItem()
url = response.url.strip()
jid = self.md5(url)
location = response.xpath(r'//ul/li[2]/strong/a/text()').extract()[0]
exp = response.xpath(r'//ul/li[5]/strong/text()').extract()[0].strip(
'年')
if '不限' in exp:
exp = 0
else:
exp = exp.strip('-')[0]
degree = response.xpath(r'//ul/li[6]/strong/text()').extract()[0]
crawled = datetime.datetime.now().strftime('%Y-%m-%d')
title = response.xpath(
r'//div[@class="inner-left fl"]/h1/text()').extract()[0].strip()
money = response.xpath(r'//ul/li[1]/strong/text()').extract()[0].strip(
'元/月\xa0')
if '以上' in money:
minmoney = maxmoney = money.strip('元/月以上')
elif '面议' in money:
minmoney = maxmoney = 0
elif '以下' in money:
minmoney = maxmoney = money.strip('元/月以下')
else:
money = money.split('-')
maxmoney = money[1].strip('元/月')
minmoney = money[0]
item['jid'] = jid
item['title'] = title
item['maxmoney'] = maxmoney
item['minmoney'] = minmoney
item['crawled'] = crawled
item['location'] = location
item['exp'] = exp
item['degree'] = degree
item['url'] = url
yield item
def parse_page(self, response):
item = ExampleItem()
item['url'] = response.url
item['title'] = response.xpath(
'/html/head/title/text()').extract_first()
m = re.match(r'(\d+)年(\d+)月份(\S+)\S车\(分制造商\)销量', item['title'])
if m is not None:
year = m.group(1)
month = m.group(2)
country = m.group(3)
conn = pymysql.Connect(host='127.0.0.1',
port=3306,
user='******',
passwd='123456',
db='car',
charset='utf8')
trs2 = response.xpath(
'//div[@class="newstext"]/table/tbody/tr/td[2]/font')
trs = response.xpath(
'//div[@class="newstext"]/table/tbody/tr/td[1]/font')
for tr in trs:
i = trs.index(tr)
logo = tr.xpath('string(.)').extract()[0]
num = trs2[i].xpath('string(.)').extract()[0]
sql = "insert into sale values('%s','%s','%s','%s','%s')" % (
year, month, country, logo, num)
cursor = conn.cursor()
try:
cursor.execute(sql)
except:
yield {'insert error': item['url']}
cursor.close()
yield {'logo': logo, 'num': num}
yield {'year': year, 'month': month, 'country': country}
conn.commit()
conn.close()
yield {'url': item['url'], 'name': item['title']}
return item
def parse_mor(self, response,mvsclass,img,name,mvUrl):
for select in response.xpath('//div[@class="contentinfo"]'):
mvdownloadUrl = select.xpath("div/table/tbody/.//tr/td/a/@href").extract() # 下载地址,可能是多个
mvdtilte = select.xpath("div/table/tbody/.//tr/td/a/text()").extract()#下载标签的文本
mvdesc = select.xpath("div[@id='text']/.//p/text()")#/p[2]/text()
desc = ''
for p in mvdesc:
desc = desc+p.extract().strip()
# desc= str(desc).replace('\\u3000',' ')
mvdownloadUrl = ";".join(mvdownloadUrl)
Item = ExampleItem()
Item['movClass'] = mvsclass
Item['downLoadName'] = name
if str(mvdtilte).strip()=='':
mvdtilte = "点击下载"
Item['downdtitle'] = str(mvdtilte)
Item['downimgurl'] = img
Item['downLoadUrl'] = mvdownloadUrl
Item['mvdesc'] = desc
Item['mvUrl'] = mvUrl
yield Item
pass
def parse(self, response):
try:
data_dict = json.loads(response.body)
except Exception as e:
print(response.body)
print(response.status)
print(e)
return
self.is_ok = True
fares = data_dict.get('fares')
journeys = jsonpath(data_dict, '$..journeys')[0]
for journey in journeys:
segments = journey.get('segments')
if len(segments) > 1:
continue
journey_key = journey.get('journeySellKey')
important = filter(lambda x: x, re.split(r'~[~|\s]*', journey_key))
carrier, fn_no, dep_port, dep_date, arr_port, arr_date = important
flight_number = carrier + fn_no
dep_time = time.mktime(time.strptime(dep_date, '%m/%d/%Y %H:%M'))
arr_time = time.mktime(time.strptime(arr_date, '%m/%d/%Y %H:%M'))
available_fares = jsonpath(segments, '$..availableFares')[0]
dep_city = self.port_city.get(dep_port, dep_port)
arr_city = self.port_city.get(arr_port, arr_port)
# 获取有座位的最低价和套餐价格
fare_index_low = None
dif_pack = []
seats = 0
for i, available_fare in enumerate(available_fares):
fare_index_temp = available_fare.get('fareIndex')
if fare_index_low is None:
fare_index_low = fare_index_temp
seats_str = available_fare.get('availableCount')
seats = 9 if seats_str == 32767 else seats_str
if i:
fare_temp = fares[fare_index_temp]
price_temp = jsonpath(fare_temp, '$..amount')[0]
seats_temp_str = available_fare.get('availableCount')
seats_temp = 9 if seats_temp_str == 32767 else seats_temp_str
dif_pack.append([price_temp, seats_temp])
fare = fares[fare_index_low]
cabin = fare.get('classOfService')
price = jsonpath(fare, '$..amount')[0]
net_fare = price
adult_tax = 0
currency = jsonpath(fare, '$..currencyCode')[0]
item = ExampleItem()
item.update(
dict(
flight_number=flight_number,
dep_time=dep_time,
arr_time=arr_time,
dep_port=dep_port,
arr_port=arr_port,
currency=currency,
adult_price=price,
adult_tax=adult_tax,
net_fare=net_fare,
max_seats=seats,
cabin=cabin,
carrier=carrier,
is_change=1,
segments=json.dumps(dif_pack),
get_time=time.time(),
from_city=dep_city,
to_city=arr_city,
info='',
))
yield item
