Scrapy项目实战之爬取某社区用户详情

from selenium import webdriver
from pymongo import MongoClient
from scrapy.crawler import overridden_settings
# from segmentfault import settings
import time
import settings

class GetCookies(object):
 def __init__(self):
  # 初始化组件
  # 设定webdriver选项
  self.opt = webdriver.ChromeOptions()
  # self.opt.add_argument("--headless")
  # 初始化用户列表
  self.user_list = settings.USER_LIST
  # 初始化MongoDB参数
  self.client = MongoClient(settings.MONGO_URI)
  self.db = self.client[settings.MONGO_DB]
  self.collection = self.db["cookies"]

 def get_cookies(self,username,password):
  """

  :param username:
  :param password:
  :return: cookies
  """
  # 使用webdriver选项创建driver
  driver = webdriver.Chrome(executable_path="/Users/Hank/scrapy/segmentfault/segmentfault/chromedriver",options=self.opt)
  driver.get("https://segmentfault.com/user/login")
  driver.find_element_by_name("username").send_keys(username)
  driver.find_element_by_name("password").send_keys(password)
  driver.find_element_by_xpath("//button[@type='submit']").click()
  time.sleep(2)
  driver.get("https://segmentfault.com/u/luwangmeilun/users/following")
  # 登陆之后获取页面cookies
  cookies = driver.get_cookies()
  driver.quit()

  return cookies

 def format_cookies(self,cookies):
  """

  :param cookies:
  从driver.get_cookies的形式为：
  [{'domain': 'segmentfault.com', 'httpOnly': False, 'name': 'PHPSESSID',
  'path': '/', 'secure': False, 'value': 'web2~5grmfa89j12eksub8hja3bvaq4'},
  {'domain': '.segmentfault.com', 'expiry': 1581602940, 'httpOnly': False,
  'name': 'Hm_lvt_e23800c454aa573c0ccb16b52665ac26', 'path': '/', 'secure': False,
  'value': '1550066940'},
  {'domain': '.segmentfault.com', 'httpOnly': False,
  'name': 'Hm_lpvt_e23800c454aa573c0ccb16b52665ac26',
  'path': '/', 'secure': False, 'value': '1550066940'},
  {'domain': '.segmentfault.com', 'expiry': 1550067000, 'httpOnly': False,
  'name': '_gat', 'path': '/', 'secure': False, 'value': '1'},
  {'domain': '.segmentfault.com', 'expiry': 1550153340, 'httpOnly': False,
  'name': '_gid', 'path': '/', 'secure': False, 'value': 'GA1.2.783265084.1550066940'},
  {'domain': '.segmentfault.com', 'expiry': 1613138940, 'httpOnly': False, 'name': '_ga',
  'path': '/', 'secure': False, 'value': 'GA1.2.1119166665.1550066940'}]
  只需提取每一项的name与value即可

  :return:
  """
  c = dict()
  for item in cookies:
   c[item['name']] = item['value']

  return c

 def save(self):
  print("开始获取Cookies....")
  # 从用户列表中获取用户名与密码，分别登陆获取cookies
  for username,password in self.user_list:
   cookies = self.get_cookies(username,password)
   f_cookies = self.format_cookies(cookies)
   print("insert cookie:{}".format(f_cookies))
   # 将格式整理后的cookies插入MongoDB数据库
   self.collection.insert_one(f_cookies)

  # s = db[self.collection].find()
  # for i in s:
  #  print(i)


if __name__ == '__main__':

 cookies = GetCookies()
 for i in range(20):
  cookies.save()

# -*- coding: utf-8 -*-

# Define here the models for your scraped items
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/items.html

import scrapy


class SegmentfaultItem(scrapy.Item):
 # define the fields for your item here like:
 # 个人属性
 # 姓名
 name = scrapy.Field()
 # 声望
 rank = scrapy.Field()
 # 学校
 school = scrapy.Field()
 # 专业
 majors = scrapy.Field()
 # 公司
 company = scrapy.Field()
 # 工作
 job = scrapy.Field()
 # blog
 blog = scrapy.Field()
 # 社交活动数据
 # 关注人数
 following = scrapy.Field()
 # 粉丝数
 fans = scrapy.Field()
 # 回答数
 answers = scrapy.Field()
 # 提问数
 questions = scrapy.Field()
 # 文章数
 articles = scrapy.Field()
 # 讲座数
 lives = scrapy.Field()
 # 徽章数
 badges = scrapy.Field()
 # 技能属性
 # 点赞数
 like = scrapy.Field()
 # 技能
 skills = scrapy.Field()
 # 注册日期
 register_date = scrapy.Field()
 # 问答统计
 # 回答最高得票数
 answers_top_score = scrapy.Field()
 # 得票数最高的回答对应的问题的标题
 answers_top_title = scrapy.Field()
 # 得票数最高的回答对应的问题的标签
 answers_top_tags = scrapy.Field()
 # 得票数最高的回答对应的问题的内容
 answers_top_question = scrapy.Field()
 # 得票数最高的回答对应的问题的内容
 answers_top_content = scrapy.Field()

# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import pymongo

class SegmentfaultPipeline(object):
 # 设定MongoDB集合名称
 collection_name = 'userinfo'

 def __init__(self,mongo_uri,mongo_db):
  self.mongo_uri = mongo_uri
  self.mongo_db = mongo_db

 # 通过crawler获取settings.py中设定的MongoDB连接信息
 @classmethod
 def from_crawler(cls,crawler):
  return cls(
   mongo_uri = crawler.settings.get('MONGO_URI'),
   mongo_db = crawler.settings.get('MONGO_DB','segmentfault')
  )

 # 当爬虫启动时连接MongoDB
 def open_spider(self,spider):
  self.client = pymongo.MongoClient(self.mongo_uri)
  self.db = self.client[self.mongo_db]

 # 当爬虫关闭时断开MongoDB连接
 def close_spider(self,spider):
  self.client.close()

 # 将Item插入数据库保存
 def process_item(self, item, spider):
  self.db[self.collection_name].insert_one(dict(item))
  return item

# -*- coding: utf-8 -*-

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

BOT_NAME = 'segmentfault'

SPIDER_MODULES = ['segmentfault.spiders']
NEWSPIDER_MODULE = 'segmentfault.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 100

# Configure a delay for requests for the same website (default: 0)
# See https://doc.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# DOWNLOAD_DELAY = 2
# The download delay setting will honor only one of:
# CONCURRENT_REQUESTS_PER_DOMAIN = 32
# CONCURRENT_REQUESTS_PER_IP = 32

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

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

RETRY_ENABLED = False

REDIRECT_ENABLED = False

DOWNLOAD_TIMEOUT = 5

# HTTPALLOW

# 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 https://doc.scrapy.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
 'segmentfault.middlewares.SegmentfaultSpiderMiddleware': 543,
}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
 # 'segmentfault.middlewares.SegmentfaultHttpProxyMiddleware': 543,
 'segmentfault.middlewares.SegmentfaultUserAgentMiddleware':643,
 'segmentfault.middlewares.SegmentfaultCookiesMiddleware':743,
 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': None,
 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
 # 'scrapy.downloadermiddlewares.cookies.CookiesMiddleware':None,

}

# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
 'segmentfault.pipelines.SegmentfaultPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://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 https://doc.scrapy.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'

# 配置MONGODB
MONGO_URI = 'localhost:27017'
MONGO_DB = 'segmentfault'

# 用户列表
USER_LIST = [
 ("798549150@qq.com","guoqing1010"),
 ("learnscrapy@163.com","guoqing1010"),
]

# 配置代理列表
PROXY_LIST = [
 'http://115.182.212.169:8080',
 'http://121.61.25.149:9999',
 'http://180.118.247.189:9000',
 'http://115.151.3.12:9999',
 'http://183.154.213.160:9000',
 'http://113.128.9.106:9999',
 'http://124.42.68.152:90',
 'http://49.70.48.50:9999',
 'http://113.128.11.172:9999',
 'http://111.177.177.40:9999',
 'http://59.62.83.253:9999',
 'http://39.107.84.185:8123',
 'http://124.94.195.107:9999',
 'http://111.177.160.132:9999',
 'http://120.25.203.182:7777'
]

USER_AGENT_LIST = [
 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60',
 'Opera/8.0 (Windows NT 5.1; U; en)',
 'Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50',
 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50',
 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0',
 'Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10',
 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36',
 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16',
 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER',
 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)',
 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)',
 'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0',
 'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)',
 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Maxthon/4.4.3.4000 Chrome/30.0.1599.101 Safari/537.36',
 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 UBrowser/4.0.3214.0 Safari/537.36'
]

# -*- coding: utf-8 -*-
import scrapy
import time
from scrapy import Request
from pymongo import MongoClient
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider,Rule
from scrapy.http import FormRequest
from segmentfault.items import SegmentfaultItem


class UserinfoSpider(CrawlSpider):
 name = 'userinfo'
 allowed_domains = ['segmentfault.com']
 start_urls = ['https://segmentfault.com/u/mybigbigcat/users/following']

 rules = (
  # 用户主页地址，跟进并进行解析
  Rule(LinkExtractor(allow=r'/u/\w+$'),callback='parse_item',follow=True),
  # 用户关注列表，跟进列表页面，抓取用户主页地址进行后续操作
  # Rule(LinkExtractor(allow=r'/users/followed$'),follow=True),
  # 用户粉丝列表，跟进列表页面，抓取用户主页地址进行后续操作
  Rule(LinkExtractor(allow=r'/users/following$'),follow=True),
  # 跟进其他页面地址
  # Rule(LinkExtractor(allow=r'/users/[followed|following]"https://segmentfault.com",
      cookies=cookies,
      meta={'cookiejar':1},
      callback=self.after_login)]

 # 登录之后从start_url中开始抓取数据
 def after_login(self,response):
  for url in self.start_urls:
   return self.make_requests_from_url(url)
 # def after_login(self,response):
 #  yield Request(self.start_urls[0],
 #     meta={'cookiejar':response.meta['cookiejar']},
 #     callback=self.parse_item)

 def parse_item(self, response):
  """
  :param response:
  :return:
  """
  item = SegmentfaultItem()
  # 个人属性模块
  profile_head = response.css('.profile__heading')
  # 姓名
  item['name'] = profile_head.css('h2[class*=name]::text').re_first(r'\w+')
  # 声望
  item['rank'] = profile_head.css('.profile__rank-btn > span::text').extract_first()
  # 学校专业信息
  school_info = profile_head.css('.profile__school::text').extract()
  if school_info:
   # 学校
   item['school'] = school_info[0]
   # 专业
   item['majors'] = school_info[1].strip()
  else:
   item['school'] = ''
   item['majors'] = ''
  # 公司职位信息
  company_info = profile_head.css('.profile__company::text').extract()
  if company_info:
   # 公司
   item['company'] = company_info[0]
   # 职位
   item['job'] = company_info[1].strip()
  else:
   item['company'] = ''
   item['job'] = ''
  # 个人博客
  item['blog'] = profile_head.css('a[class*=other-item-link]::attr(href)').extract_first()

  # 统计面板模块
  profile_active = response.xpath("//div[@class='col-md-2']")
  # 关注人数
  item['following'] = profile_active.css('div[class*=info] a > .h5::text').re(r'\d+')[0]
  # 粉丝人数
  item['fans'] = profile_active.css('div[class*=info] a > .h5::text').re(r'\d+')[1]
  # 回答问题数
  item['answers'] = profile_active.css('a[href*=answer] .count::text').re_first(r'\d+')
  # 提问数
  item['questions'] = profile_active.css('a[href*=questions] .count::text').re_first(r'\d+')
  # 文章数
  item['articles'] = profile_active.css('a[href*=articles] .count::text').re_first(r'\d+')
  # 讲座数
  item['lives'] = profile_active.css('a[href*=lives] .count::text').re_first(r'\d+')
  # 徽章数
  item['badges'] = profile_active.css('a[href*=badges] .count::text').re_first(r'\d+')
  # 徽章详细页面地址
  badge_url = profile_active.css('a[href*=badges]::attr(href)').extract_first()

  # 技能面板模块
  profile_skill = response.xpath("//div[@class='col-md-3']")
  # 技能标签列表
  item['skills'] = profile_skill.css('.tag::text').re(r'\w+')
  # 获得的点赞数
  item['like'] = profile_skill.css('.authlist').re_first(r'获得 (\d+) 次点赞')
  # 注册日期
  item['register_date'] = profile_skill.css('.profile__skill--other p::text').extract_first()
  # if register_time:
  #  item['register_date'] = ''.join(re.findall(r'\d+',register_time))
  # else:
  #  item['register_date'] = ''

  # 产出数据模块
  profile_work = response.xpath("//div[@class='col-md-7']")
  # 回答获得的最高分
  item['answers_top_score'] = profile_work.css('#navAnswer .label::text').re_first(r'\d+')
  # 最高分回答对应的问题的标题
  item['answers_top_title'] = profile_work.css('#navAnswer div[class*=title-warp] > a::text').extract_first()
  # 最高分回答对应的问题的url
  answer_url = profile_work.css('#navAnswer div[class*=title-warp] > a::attr(href)').extract_first()

  # 将需要继续跟进抓取数据的url与item作为参数传递给相应方法继续抓取数据
  request = scrapy.Request(
   # 问题详细页url
   url=response.urljoin(answer_url),
   meta={
   # item需要传递
   'item':item,
   # 徽章的url
   'badge_url':response.urljoin(badge_url)},
   # 调用parse_ansser继续处理
   callback=self.parse_answer)
  yield request

 def parse_answer(self,response):
  # 取出传递的item
  item = response.meta['item']
  # 取出传递的徽章详细页url
  badge_url = response.meta['badge_url']
  # 问题标签列表
  item['answers_top_tags'] = response.css('.question__title--tag .tag::text').re(r'\w+')
  # 先获取组成问题内容的字符串列表
  question_content = response.css('.widget-question__item p').re(r'>(.*"htmlcode">

# -*- coding: utf-8 -*-

# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
import random
import re
import datetime
import scrapy
import logging
import time
from scrapy.conf import settings
from pymongo import MongoClient
from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware
import pymongo
logger = logging.getLogger(__name__)


class SegmentfaultSpiderMiddleware(object):
 """
 处理Item中保存的三种类型注册日期数据：
 1. 注册于 2015年12月12日
 2. 注册于 3 天前
 3. 注册于 5 小时前
 """

 def process_spider_output(self,response,result,spider):

  """
  输出response时调用此方法处理item中register_date
  :param response:
  :param result: 包含item
  :param spider:
  :return:处理过注册日期的item
  """
  for item in result:
   # 判断获取的数据是否是scrapy.item类型
   if isinstance(item,scrapy.Item):
    # 获取当前时间
    now = datetime.datetime.now()
    register_date = item['register_date']
    logger.info("获取注册日志格式为{}".format(register_date))
    # 提取注册日期字符串，如'注册于2015年12月12日' => '20151212'
    day = ''.join(re.findall(r'\d+',register_date))
    # 如果提取数字字符串长度大于4位，则为'注册于2015年12月12日'形式
    if len(day) > 4:
     date = day
    # 如果‘时'在提取的字符串中，则为'注册于8小时前'形式
    elif '时' in register_date:
     d = now - datetime.timedelta(hours=int(day))
     date = d.strftime("%Y%m%d")
    # 最后一种情况就是'注册于3天前'形式
    else:
     d = now - datetime.timedelta(days=int(day))
     date = d.strftime("%Y%m%d")

    # 更新register_date值
    item['register_date'] = date
   yield item


class SegmentfaultHttpProxyMiddleware(object):
 # Not all methods need to be defined. If a method is not defined,
 # scrapy acts as if the downloader middleware does not modify the
 # passed objects.
 def __init__(self):
  self.proxy_list = settings['PROXY_LIST']

 def process_request(self, request, spider):
  proxy = random.choice(self.proxy_list)
  logger.info('使用代理:{}'.format(proxy))
  request.meta['proxy'] = proxy


class SegmentfaultUserAgentMiddleware(object):
 def __init__(self):
  self.useragent_list = settings['USER_AGENT_LIST']

 def process_request(self,request,spider):
  user_agent = random.choice(self.useragent_list)

  # logger.info('使用的USE USER-AGENT:{}'.format(user_agent))
  request.headers['User-Agent'] = user_agent



class SegmentfaultCookiesMiddleware(object):
 client = MongoClient(settings['MONGO_URI'])
 db = client[settings['MONGO_DB']]
 collection = db['cookies']

 def get_cookies(self):
  """
  随机获取cookies
  :return:
  """
  cookies = random.choice([cookie for cookie in self.collection.find()])
  # 将不需要的"_id"与"_gat"参数删除
  cookies.pop('_id')
  cookies.pop('_gat')
  # 将"Hm_lpvt_e23800c454aa573c0ccb16b52665ac26"填充当前时间
  cookies['Hm_lpvt_e23800c454aa573c0ccb16b52665ac26'] = str(int(time.time()))
  return cookies

 def remove_cookies(self,cookies):
  """
  删除已失效的cookies
  :param cookies:
  :return:
  """
  # 随机获取cookies中的一对键值,返回结果是一个元祖
  i = cookies.popitem()
  # 删除cookies
  try:
   logger.info("删除cookies{}".format(cookies))
   self.collection.remove({i[0]:i[1]})
  except Exception as e:
   logger.info("No this cookies:{}".format(cookies))

 def process_request(self,request,spider):
  """
  为每一个request添加一个cookie
  :param request:
  :param spider:
  :return:
  """
  cookies = self.get_cookies()
  request.cookies = cookies

 def process_response(self,request,response,spider):
  """
  对于登录失效的情况，可能会重定向到登录页面，这时添加新的cookies继续，将请求放回调度器
  :param request:
  :param response:
  :param spider:
  :return:
  """
  if response.status in [301,302]:
   logger.info("Redirect response:{}".format(response))
   redirect_url = response.headers['location']
   if b'/user/login' in redirect_url:
    logger.info("Cookies失效")

    # 请求失败，重新获取一个cookie，添加到request，并停止后续中间件处理此request，将此request放入调度器
    new_cookie = self.get_cookies()
    logger.info("获取新cookie:{}".format(new_cookie))
    # 删除旧cookies
    self.remove_cookies(request.cookies)
    request.cookies = new_cookie
   return request
  #
  return response



run.py




from scrapy import cmdline
# from segmentfault.get_cookies import GetCookies
from get_cookies import GetCookies

if __name__ == '__main__':
 cookies = GetCookies()
 cookies.save()
 name = 'userinfo'
 ""
 cmd = 'scrapy crawl {}'.format(name)
 cmdline.execute(cmd.split())