首页 > 代码库 > scrapy实战1分布式爬取有缘网:

scrapy实战1分布式爬取有缘网:

直接上代码:

items.py

技术分享
 1 # -*- coding: utf-8 -*-
 2 
 3 # Define here the models for your scraped items
 4 #
 5 # See documentation in:
 6 # http://doc.scrapy.org/en/latest/topics/items.html
 7 
 8 import scrapy
 9 
10 
11 class YouyuanwangItem(scrapy.Item):
12     # define the fields for your item here like:
13     # name = scrapy.Field()
14     # 个人头像链接
15     header_url=scrapy.Field()
16     # 用户名
17     username=scrapy.Field()
18     # 内心独白
19     monologue=scrapy.Field()
20     # 相册图片链接
21     pic_urls=scrapy.Field()
22     #籍贯
23     place_from=scrapy.Field()
24     #学历
25     education=scrapy.Field()
26     # 年龄
27     age=scrapy.Field()
28     #身高
29     height=scrapy.Field()
30     #工资
31     salary=scrapy.Field()
32     #兴趣爱好
33     hobby=scrapy.Field()
34     # 网站来源 youyuan
35     source=scrapy.Field()
36     # 个人主页源url
37     source_url=scrapy.Field()
38     # 爬虫名
39     spider=scrapy.Field()
View Code

spiders >yuoyuan.py

技术分享
  1 # -*- coding: utf-8 -*-
  2 import scrapy
  3 from scrapy.linkextractors import LinkExtractor
  4 from scrapy.spiders import Rule,CrawlSpider
  5 #from scrapy_redis.spiders import RedisCrawlSpider
  6 from youyuanwang.items import YouyuanwangItem
  7 
  8 
  9 class YouyuanSpider(CrawlSpider):
 10 #class YouyuanSpider(RedisCrawlSpider):
 11     name = youyuan
 12     allowed_domains = [www.youyuan.com]
 13     # 有缘网的列表页
 14     start_urls = [http://www.youyuan.com/find/beijing/mm18-25/advance-0-0-0-0-0-0-0/p1/]
 15     #redis_key = ‘YouyuanSpider:start_urls‘
 16     #动态域范围的获取
 17     # def __init__(self, *args, **kwargs):
 18     #     # Dynamically define the allowed domains list.
 19     #     domain = kwargs.pop(‘domain‘, ‘‘)
 20     #     self.allowed_domains = filter(None, domain.split(‘,‘))
 21     #     super(YouyuanSpider, self).__init__(*args, **kwargs)
 22     #匹配全国
 23     #list_page = LinkExtractor(allow=(r‘http://www.youyuan.com/find/.+‘))
 24     # 只匹配北京、18~25岁、女性 的 搜索页面匹配规则,根据response提取链接
 25     page_links=LinkExtractor(allow=r"http://www.youyuan.com/find/beijing/mm18-25/advance-0-0-0-0-0-0-0/p\d+/")
 26     # 个人主页 匹配规则,根据response提取链接
 27     profile_page=LinkExtractor(allow=r"http://www.youyuan.com/\d+-profile/")
 28 
 29     rules = (
 30         # 匹配列表页成功,跟进链接,跳板
 31         Rule(page_links),
 32         # 匹配个人主页的链接,形成request保存到redis中等待调度,一旦有响应则调用parse_profile_page()回调函数处理,不做继续跟进
 33         Rule(profile_page,callback="parse_profile_page",follow=False)
 34     )
 35 
 36     # 处理个人主页信息,得到我们要的数据
 37     def parse_profile_page(self, response):
 38         item=YouyuanwangItem()
 39         # 个人头像链接
 40         item[header_url]=self.get_header_url(response)
 41         # 用户名
 42         item[username]=self.get_username(response)
 43         #籍贯
 44         item[place_from]=self.get_place_from(response)
 45         #学历
 46         item[education]=self.get_education(response)
 47 
 48         # 年龄
 49         item[age]=self.get_age(response)
 50         # 身高
 51         item[height]=self.get_height(response)
 52         # 工资
 53         item[salary]=self.get_salary(response)
 54         # 兴趣爱好
 55         item[hobby]=self.get_hobby(response)
 56         # 相册图片链接
 57         item[pic_urls] = self.get_pic_urls(response)
 58         # 内心独白
 59         item[monologue] = self.get_monologue(response)
 60         # 个人主页源url
 61         item[source_url]=response.url
 62         # 网站来源 youyuan
 63         item[source]="youyuan"
 64         # 爬虫名
 65         item[spider]="youyuan"
 66         yield item
 67    #提取头像地址
 68     def get_header_url(self,response):
 69         header=response.xpath(//dl[@class="personal_cen"]/dt/img/@src).extract()
 70         if len(header):
 71             header_url=header[0]
 72         else:
 73             header_url= ""
 74         return header_url.strip()
 75     #提取用户名
 76     def get_username(self,response):
 77         username=response.xpath(//dl[@class="personal_cen"]/dd//div[@class="main"]/strong/text()).extract()
 78         if len(username):
 79             username=username[0]
 80         else:
 81             username=""
 82         return username.strip()
 83     #提取年龄
 84     def get_age(self,response):
 85         age=response.xpath(//dl[@class="personal_cen"]//p[@class="local"]/text()).extract()
 86         if len(age):
 87             age=age[0].split()[1]
 88         else:
 89             age=""
 90         return age
 91     #提取身高
 92     def get_height(self,response):
 93         height=response.xpath(//div[@class="pre_data"]/ul/li[2]/div/ol[2]/li[2]/span/text()).extract()
 94         if len(height):
 95             height=height[0]
 96         else:
 97             height=""
 98 
 99         return height.strip()
100     #提取工资
101     def get_salary(self,response):
102         salary=response.xpath(//div[@class="pre_data"]/ul/li[2]/div/ol[1]/li[4]/span/text()).extract()
103         if len(salary):
104             salary=salary[0]
105         else:
106             salary=""
107         return salary.strip()
108     #提取兴趣爱好
109     def get_hobby(self,response):
110         hobby=response.xpath(//dl[@class="personal_cen"]//ol[@class="hoby"]//li/text()).extract()
111         if len(hobby):
112             hobby=",".join(hobby).replace(" ","")
113         else:
114             hobby=""
115         return hobby.strip()
116     #提取相册图片
117     def get_pic_urls(self,response):
118         pic_urls=response.xpath(//div[@class="ph_show"]/ul/li/a/img/@src).extract()
119         if len(pic_urls):
120             pic_urls=",".join(pic_urls)
121             #将相册url列表转换成字符串
122         else:
123             pic_urls=""
124         return pic_urls
125     #提取内心独白
126     def get_monologue(self,response):
127         monologue=response.xpath(//div[@class="pre_data"]/ul/li/p/text()).extract()
128         if len(monologue):
129             monologue=monologue[0]
130         else:
131             monologue=""
132         return monologue.strip()
133     #提取籍贯
134     def get_place_from(self,response):
135         place_from=response.xpath(//div[@class="pre_data"]/ul/li[2]/div/ol[1]/li[1]/span/text()).extract()
136         if len(place_from):
137             place_from=place_from[0]
138         else:
139             place_from=""
140         return place_from.strip()
141     #提取学历
142     def get_education(self,response):
143         education=response.xpath(//div[@class="pre_data"]/ul/li[2]/div/ol[1]/li[3]/span/text()).extract()
144         if len(education):
145             education=education[0]
146         else:
147             education=""
148         return education.strip()
View Code

pipelines.py

技术分享
 1 # -*- coding: utf-8 -*-
 2 
 3 # Define your item pipelines here
 4 #
 5 # Don‘t forget to add your pipeline to the ITEM_PIPELINES setting
 6 # See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
 7 # import json
 8 #
 9 # class YouyuanwangPipeline(object):
10 #     def __init__(self):
11 #         self.filename=open("youyuanwang.json","wb")
12 #     def process_item(self, item, spider):
13 #         jsontext=json.dumps(dict(item),ensure_ascii=False) + ",\n"
14 #         self.filename.write(jsontext.encode("utf-8"))
15 #         return item
16 #     def close_spider(self,spider):
17 #         self.filename.close()
18 
19 import pymysql
20 from .models.es_types import YouyuanType
21 class XiciPipeline(object):
22     def process_item(self, item, spider):
23         # DBKWARGS=spider.settings.get(‘DBKWARGS‘)
24         con=pymysql.connect(host=127.0.0.1,user=root,passwd=229801,db=yunyuan,charset=utf8)
25         cur=con.cursor()
26         sql=("insert into youyuanwang(header_url,username,monologue,pic_urls,place_from,education,age,height,salary,hobby,source)"
27              "VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)")
28         lis=(item[header_url],item[username],item[monologue],item[pic_urls],item[place_from],item[education],item[age],item[height],item[salary],item[hobby],item[source])
29 
30         cur.execute(sql,lis)
31         con.commit()
32         cur.close()
33         con.close()
34         return item
35 
36 
37 
38 class ElasticsearchPipeline(object):
39     def process_item(self,item,spider):
40         youyuan = YouyuanType()
41         youyuan.header_url=item["header_url"]
42         youyuan.username=item["username"]
43         youyuan.age=item["age"]
44         youyuan.salary=item["salary"]
45         youyuan.monologue=item["monologue"]
46         youyuan.pic_urls=item["pic_urls"]
47         youyuan.place_from=item["place_from"]
48 
49         youyuan.save()
50 
51         return item
View Code

settings.py

技术分享
# -*- coding: utf-8 -*-

# Scrapy settings for youyuanwang project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

BOT_NAME = youyuanwang

SPIDER_MODULES = [youyuanwang.spiders]
NEWSPIDER_MODULE = youyuanwang.spiders


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = ‘youyuanwang (+http://www.yourdomain.com)‘

# Obey robots.txt rules
#ROBOTSTXT_OBEY = True

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   ‘Accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8‘,
#   ‘Accept-Language‘: ‘en‘,
#}

# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    ‘youyuanwang.middlewares.YouyuanwangSpiderMiddleware‘: 543,
#}

# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    ‘youyuanwang.middlewares.MyCustomDownloaderMiddleware‘: 543,
#}

# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    ‘scrapy.extensions.telnet.TelnetConsole‘: None,
#}
 DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
 SCHEDULER = "scrapy_redis.scheduler.Scheduler"
 SCHEDULER_PERSIST = True

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   #‘youyuanwang.pipelines.XiciPipeline‘: 300,
   youyuanwang.pipelines.ElasticsearchPipeline: 300,
   # ‘scrapy_redis.pipelines.RedisPipeline‘:400,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = ‘httpcache‘
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = ‘scrapy.extensions.httpcache.FilesystemCacheStorage‘
View Code

从redis保存到mongodb 在目录下新建文件process_item_mongo.py(名字随便取)

技术分享
 1 #coding=utf-8
 2 
 3 
 4 import pymongo
 5 import redis
 6 import json
 7 
 8 def process_item():
 9     Redis_conn=redis.StrictRedis(host=127.0.0.1,port=6379,db=0)
10     Mongo_conn=pymongo.MongoClient(host=127.0.0.1,port=27017)
11     db=Mongo_conn["youyuan"]
12     table=db["beijing_18_25"]
13     while True:
14         source, data = http://www.mamicode.com/Redis_conn.blpop(["youyuan:items"])
15         data = http://www.mamicode.com/json.loads(data.decode("utf-8"))
16         table.insert(data)
17 if __name__=="__main__":
18     process_item()
View Code

从redis保存到mysql 在目录下新建文件process_item_mysql.py(名字随便取)

技术分享
 1 #coding=utf-8
 2 
 3 import pymysql
 4 import redis
 5 import json
 6 
 7 def process_item():
 8     Redis_conn=redis.StrictRedis(host=127.0.0.1,port=6379,db=0)
 9     MySql_conn=pymysql.connect(host=127.0.0.1,user=root,passwd=229801,port=3306,db=yunyuan)
10     while True:
11         source,data=http://www.mamicode.com/Redis_conn.blpop("youyuan:items")
12         data=http://www.mamicode.com/json.loads(data.decode("utf-8"))
13         cur=MySql_conn.cursor()
14         sql=("insert into youyuanwang(header_url,username,monologue,pic_urls,place_from,education,age,height,salary,hobby,source)"
15              "VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)")
16         lis = (data[header_url], data[username], data[monologue], data[pic_urls], data[place_from],
17                data[education], data[age], data[height], data[salary], data[hobby], data[source])
18         cur.execute(sql,lis)
19         MySql_conn.commit()
20         cur.close()
21         MySql_conn.close()
22     if __name__=="__main__":
23         process_item()
View Code

 数据:

技术分享

申明:以上只限于参考学习交流!!!

scrapy实战1分布式爬取有缘网: