Scrapy框架CrawlSpiders的介绍以及使用详解

源码解析class CrawlSpider(Spider):  rules = ()  def __init__(self, *a, **kw):    super(CrawlSpider, self).__init__(*a, **kw)    self._compile_rules()  # 首先调用parse()来处理start_urls中返回的response对象  # parse()则将这些response对象传递给了_parse_response()函数处理，并设置回调函数为parse_start_url()  # 设置了跟进标志位True  # parse将返回item和跟进了的Request对象    def parse(self, response):    return self._parse_response(response, self.parse_start_url, cb_kwargs={}, follow=True)  # 处理start_url中返回的response，需要重写  def parse_start_url(self, response):    return []  def process_results(self, response, results):    return results  # 从response中抽取符合任一用户定义'规则'的链接，并构造成Resquest对象返回  def _requests_to_follow(self, response):    if not isinstance(response, HtmlResponse):      return    seen = set()    # 抽取之内的所有链接，只要通过任意一个'规则'，即表示合法    for n, rule in enumerate(self._rules):      links = [l for l in rule.link_extractor.extract_links(response) if l not in seen]      # 使用用户指定的process_links处理每个连接      if links and rule.process_links:        links = rule.process_links(links)      # 将链接加入seen集合，为每个链接生成Request对象，并设置回调函数为_repsonse_downloaded()      for link in links:        seen.add(link)        # 构造Request对象，并将Rule规则中定义的回调函数作为这个Request对象的回调函数        r = Request(url=link.url, callback=self._response_downloaded)        r.meta.update(rule=n, link_text=link.text)        # 对每个Request调用process_request()函数。该函数默认为indentify，即不做任何处理，直接返回该Request.        yield rule.process_request(r)  # 处理通过rule提取出的连接，并返回item以及request  def _response_downloaded(self, response):    rule = self._rules[response.meta['rule']]    return self._parse_response(response, rule.callback, rule.cb_kwargs, rule.follow)  # 解析response对象，会用callback解析处理他，并返回request或Item对象  def _parse_response(self, response, callback, cb_kwargs, follow=True):    # 首先判断是否设置了回调函数。（该回调函数可能是rule中的解析函数，也可能是 parse_start_url函数）    # 如果设置了回调函数（parse_start_url()），那么首先用parse_start_url()处理response对象，    # 然后再交给process_results处理。返回cb_res的一个列表    if callback:      #如果是parse调用的，则会解析成Request对象      #如果是rule callback，则会解析成Item      cb_res = callback(response, **cb_kwargs) or ()      cb_res = self.process_results(response, cb_res)      for requests_or_item in iterate_spider_output(cb_res):        yield requests_or_item    # 如果需要跟进，那么使用定义的Rule规则提取并返回这些Request对象    if follow and self._follow_links:      #返回每个Request对象      for request_or_item in self._requests_to_follow(response):        yield request_or_item  def _compile_rules(self):    def get_method(method):      if callable(method):        return method      elif isinstance(method, basestring):        return getattr(self, method, None)    self._rules = [copy.copy(r) for r in self.rules]    for rule in self._rules:      rule.callback = get_method(rule.callback)      rule.process_links = get_method(rule.process_links)      rule.process_request = get_method(rule.process_request)  def set_crawler(self, crawler):    super(CrawlSpider, self).set_crawler(crawler)    self._follow_links = crawler.settings.getbool('CRAWLSPIDER_FOLLOW_LINKS', True)

class scrapy.linkextractors.LinkExtractor(  allow = (),  deny = (),  allow_domains = (),  deny_domains = (),  deny_extensions = None,  restrict_xpaths = (),  tags = ('a','area'),  attrs = ('href'),  canonicalize = True,  unique = True,  process_value = None)

class scrapy.spiders.Rule(    link_extractor,     callback = None,     cb_kwargs = None,     follow = None,     process_links = None,     process_request = None)

LOG_FILE = "TencentSpider.log"LOG_LEVEL = "INFO"

模型类import scrapyclass CrawlyouyuanItem(scrapy.Item):  # 用户名  username = scrapy.Field()  # 年龄  age = scrapy.Field()  # 头像图片的链接  header_url = scrapy.Field()  # 相册图片的链接  images_url = scrapy.Field()  # 内心独白  content = scrapy.Field()  # 籍贯  place_from = scrapy.Field()  # 学历  education = scrapy.Field()  # 兴趣爱好  hobby = scrapy.Field()  # 个人主页  source_url = scrapy.Field()  # 数据来源网站  sourec = scrapy.Field()  # utc 时间  time = scrapy.Field()  # 爬虫名  spidername = scrapy.Field()

爬虫文件# -*- coding: utf-8 -*-import scrapyfrom scrapy.linkextractors import LinkExtractorfrom scrapy.spiders import CrawlSpider, Rulefrom CrawlYouYuan.items import CrawlyouyuanItemimport reclass YouyuanSpider(CrawlSpider):  name = 'youyuan'  allowed_domains = ['youyuan.com']  start_urls = ['http://www.youyuan.com/find/beijing/mm18-25/advance-0-0-0-0-0-0-0/p1/']  # 自动生成的文件不需要改东西，只需要添加rules文件里面Rule角色就可以  # 每一页匹配规则  page_links = LinkExtractor(allow=(r"youyuan.com/find/beijing/mm18-25/advance-0-0-0-0-0-0-0/p/d+/"))  # 每个人个人主页匹配规则  profile_links = LinkExtractor(allow=(r"youyuan.com//d+-profile/"))  rules = (    # 没有回调函数，说明follow是True    Rule(page_links),    # 有回调函数，说明follow是False    Rule(profile_links, callback='parse_item', follow=True),  )  def parse_item(self, response):    item = CrawlyouyuanItem()    item['username'] = self.get_username(response)    # 年龄    item['age'] = self.get_age(response)    # 头像图片的链接    item['header_url'] = self.get_header_url(response)    # 相册图片的链接    item['images_url'] = self.get_images_url(response)    # 内心独白    item['content'] = self.get_content(response)    # 籍贯    item['place_from'] = self.get_place_from(response)    # 学历    item['education'] = self.get_education(response)    # 兴趣爱好    item['hobby'] = self.get_hobby(response)    # 个人主页    item['source_url'] = response.url    # 数据来源网站    item['sourec'] = "youyuan"    yield item  def get_username(self, response):    username = response.xpath("//dl[@class='personal_cen']//div[@class='main']/strong/text()").extract()    if len(username):      username = username[0]    else:      username = "NULL"    return username.strip()  def get_age(self, response):    age = response.xpath("//dl[@class='personal_cen']//dd/p/text()").extract()    if len(age):      age = re.findall(u"/d+岁", age[0])[0]    else:      age = "NULL"    return age.strip()  def get_header_url(self, response):    header_url = response.xpath("//dl[@class='personal_cen']/dt/img/@src").extract()    if len(header_url):      header_url = header_url[0]    else:      header_url = "NULL"    return header_url.strip()  def get_images_url(self, response):    images_url = response.xpath("//div[@class='ph_show']/ul/li/a/img/@src").extract()    if len(images_url):      images_url = ", ".join(images_url)    else:      images_url = "NULL"    return images_url  def get_content(self, response):    content = response.xpath("//div[@class='pre_data']/ul/li/p/text()").extract()    if len(content):      content = content[0]    else:      content = "NULL"    return content.strip()  def get_place_from(self, response):    place_from = response.xpath("//div[@class='pre_data']/ul/li[2]//ol[1]/li[1]/span/text()").extract()    if len(place_from):      place_from = place_from[0]    else:      place_from = "NULL"    return place_from.strip()  def get_education(self, response):    education = response.xpath("//div[@class='pre_data']/ul/li[3]//ol[2]/li[2]/span/text()").extract()    if len(education):      education = education[0]    else:      education = "NULL"    return education.strip()  def get_hobby(self, response):    hobby = response.xpath("//dl[@class='personal_cen']//ol/li/text()").extract()    if len(hobby):      hobby = ",".join(hobby).replace(" ", "")    else:      hobby = "NULL"    return hobby.strip()

管道文件import jsonimport codecsclass CrawlyouyuanPipeline(object):  def __init__(self):    self.filename = codecs.open('content.json', 'w', encoding='utf-8')  def process_item(self, item, spider):    html = json.dumps(dict(item), ensure_ascii=False)    self.filename.write(html + '/n')    return item  def spider_closed(self, spider):    self.filename.close()

BOT_NAME = 'CrawlYouYuan'SPIDER_MODULES = ['CrawlYouYuan.spiders']NEWSPIDER_MODULE = 'CrawlYouYuan.spiders'# Crawl responsibly by identifying yourself (and your website) on the user-agentUSER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:56.0)'# Obey robots.txt rulesROBOTSTXT_OBEY = TrueITEM_PIPELINES = {  'CrawlYouYuan.pipelines.CrawlyouyuanPipeline': 300,}

from scrapy import cmdlinecmdline.execute('scrapy crawl youyuan'.split())