Scrapy的spider(蜘蛛)基类源码
一旦spider的子类被实例化,__ init __ 中的代码就会被执行,所以需要设定name和 star_url 两个属性。然而Spider 的子类被实例化后并不会马上被执行爬网,只有在 start_requests 被调用时,蜘蛛才会执行爬网。
如果想修改最初爬取某个网站的 REquests 对象,则可以重写(override)start_requests 函数。
"""
Base class for Scrapy spiders
See documentation in docs/topics/spiders.rst
"""
import logging
import warnings
from scrapy import signals
from scrapy.http import Request
from scrapy.utils.trackref import object_ref
from scrapy.utils.url import url_is_from_spider
from scrapy.utils.deprecate import create_deprecated_class
from scrapy.exceptions import ScrapyDeprecationWarning
from scrapy.utils.deprecate import method_is_overridden
class Spider(object_ref):
"""
Base class for scrapy spiders. All spiders must inherit from this
class.
"""
name = None
custom_settings = None
def __init__(self, name=None, **kwargs):
if name is not None:
self.name = name
elif not getattr(self, 'name', None):
raise ValueError("%s must have a name" % type(self).__name__)
self.__dict__.update(kwargs)
if not hasattr(self, 'start_urls'):
self.start_urls = []
@property
def logger(self):
logger = logging.getLogger(self.name)
return logging.LoggerAdapter(logger, {'spider': self})
def log(self, message, level=logging.DEBUG, **kw):
"""
Log the given message at the given log level
This helper wraps a log call to the logger within the spider, but you
can use it directly (e.g. Spider.logger.info('msg')) or use any other
Python logger too.
"""
self.logger.log(level, message, **kw)
@classmethod
def from_crawler(cls, crawler, *args, **kwargs):
spider = cls(*args, **kwargs)
spider._set_crawler(crawler)
return spider
def set_crawler(self, crawler):
warnings.warn("set_crawler is deprecated, instantiate and bound the "
"spider to this crawler with from_crawler method "
"instead.",
category=ScrapyDeprecationWarning, stacklevel=2)
assert not hasattr(self, 'crawler'), "Spider already bounded to a " \
"crawler"
self._set_crawler(crawler)
def _set_crawler(self, crawler):
self.crawler = crawler
self.settings = crawler.settings
crawler.signals.connect(self.close, signals.spider_closed)
def start_requests(self):
cls = self.__class__
if method_is_overridden(cls, Spider, 'make_requests_from_url'):
warnings.warn(
"Spider.make_requests_from_url method is deprecated; it "
"won't be called in future Scrapy releases. Please "
"override Spider.start_requests method instead (see %s.%s)." % (
cls.__module__, cls.__name__
),
)
for url in self.start_urls:
yield self.make_requests_from_url(url)
else:
for url in self.start_urls:
yield Request(url, dont_filter=True)
def make_requests_from_url(self, url):
""" This method is deprecated. """
return Request(url, dont_filter=True)
def parse(self, response):
raise NotImplementedError
@classmethod
def update_settings(cls, settings):
settings.setdict(cls.custom_settings or {}, priority='spider')
@classmethod
def handles_request(cls, request):
return url_is_from_spider(request.url, cls)
@staticmethod
def close(spider, reason):
closed = getattr(spider, 'closed', None)
if callable(closed):
return closed(reason)
def __str__(self):
return "<%s %r at 0x%0x>" % (type(self).__name__, self.name, id(self))
__repr__ = __str__
修改start_requests ,调用时以post 登录 :
def start_requests (self):
return [scrapy.FormRequest("http://www.wxample.com/login",
formadta = {'user':'jon','pass':'secret'},
callback = self.logged_in)]
'''
接收一个URL并返回用于爬取的requests对象。在初始化request时被start_requests()调用,
也被用于i转化url为request。
'''
通用蜘蛛
scrapy提供了4个通用的蜘蛛来处理一些普遍的爬取任务:
XMLFeedSpider —— 用于爬取XML文档格式的蜘蛛基类
CSVFeedSpider —— 用于CSV 文件的爬取
CrawlSpider —— 用于进行间接式爬取的蜘蛛
SitemapSpider —— 从Sitemap.xml文件跟进入网站进行深度爬网的蜘蛛