04| scrapy start_urls和中间键

 

 

scrapy引擎来爬虫中取起始URL：

　　1. 调用start_requests并获取返回值
　　2. v = iter(返回值)
　　3. 
　　　　req1 = 执行 v.__next__()
　　　　req2 = 执行 v.__next__()
　　　　req3 = 执行 v.__next__()
...
　　4. req全部放到调度器中　　

　　

源码

    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)

　　

我们可以实现自定义

def start_requests(self):
    url = 'http://dig.chouti.com/'
    yield Request(url=url, callback=self.login, meta={'cookiejar': True})

　　

- 定制：可以去redis中获取start_url

深度和优先级

- 深度 
	- 最开始是0
	- 每次yield时，会根据原来请求中的depth + 1
- 配置：DEPTH_LIMIT 深度控制
　　 优先级		
　　　　- 请求被下载的优先级 -= 深度 * 配置 DEPTH_PRIORITY 
	配置：DEPTH_PRIORITY 

　　

from scrapy.spidermiddlewares.depth import DepthMiddleware

class DepthMiddleware(object):

    def __init__(self, maxdepth, stats=None, verbose_stats=False, prio=1):
        self.maxdepth = maxdepth
        self.stats = stats
        self.verbose_stats = verbose_stats
        self.prio = prio

    @classmethod
    def from_crawler(cls, crawler):
        settings = crawler.settings
        maxdepth = settings.getint('DEPTH_LIMIT')
        verbose = settings.getbool('DEPTH_STATS_VERBOSE')
        prio = settings.getint('DEPTH_PRIORITY')
        return cls(maxdepth, crawler.stats, verbose, prio)
　　 #　每次经过中间键的时候，都会执行这个方法
    def process_spider_output(self, response, result, spider):
        def _filter(request):
            if isinstance(request, Request):
                depth = response.meta['depth'] + 1
                request.meta['depth'] = depth
                if self.prio:
                    request.priority -= depth * self.prio
                if self.maxdepth and depth > self.maxdepth:
                    logger.debug(
                        "Ignoring link (depth > %(maxdepth)d): %(requrl)s ",
                        {'maxdepth': self.maxdepth, 'requrl': request.url},
                        extra={'spider': spider}
                    )
                    return False
                elif self.stats:
                    if self.verbose_stats:
                        self.stats.inc_value('request_depth_count/%s' % depth,
                                             spider=spider)
                    self.stats.max_value('request_depth_max', depth,
                                         spider=spider)
            return True

        # base case (depth=0)　如果没传则赋值为 0　
        if self.stats and 'depth' not in response.meta:
            response.meta['depth'] = 0
            if self.verbose_stats:
                self.stats.inc_value('request_depth_count/0', spider=spider)

        return (r for r in result or () if _filter(r))

　　

from scrapy.http import Response　我们可以看到response.mata = request.meta

class Response(object_ref):

    def __init__(self, url, status=200, headers=None, body=b'', flags=None, request=None):
        self.headers = Headers(headers or {})
        self.status = int(status)
        self._set_body(body)
        self._set_url(url)
        self.request = request
        self.flags = [] if flags is None else list(flags)

    @property
    def meta(self):
        try:
            return self.request.meta

　　

内置代理

 1  在环境变量中添加，在爬虫启动时，提前在os.envrion中设置代理即可。

class ChoutiSpider(scrapy.Spider):
	name = 'chouti'
	allowed_domains = ['chouti.com']
	start_urls = ['https://dig.chouti.com/']
	cookie_dict = {}

	def start_requests(self):
		import os
		os.environ['HTTPS_PROXY'] = "http://root:woshiniba@192.168.11.11:9999/"
		os.environ['HTTP_PROXY'] = '19.11.2.32',
		for url in self.start_urls:
			yield Request(url=url,callback=self.parse)

2  在meta中添加

class ChoutiSpider(scrapy.Spider):
	name = 'chouti'
	allowed_domains = ['chouti.com']
	start_urls = ['https://dig.chouti.com/']
	cookie_dict = {}

	def start_requests(self):
		for url in self.start_urls:
			yield Request(url=url,callback=self.parse,meta={'proxy':'"http://root:woshiniba@192.168.11.11:9999/"'})

　　

自定义代理

 

# by luffycity.com
import base64
import random
from six.moves.urllib.parse import unquote
try:
    from urllib2 import _parse_proxy
except ImportError:
    from urllib.request import _parse_proxy
from six.moves.urllib.parse import urlunparse
from scrapy.utils.python import to_bytes

class XdbProxyMiddleware(object):

    def _basic_auth_header(self, username, password):
        user_pass = to_bytes(
            '%s:%s' % (unquote(username), unquote(password)),
            encoding='latin-1')
        return base64.b64encode(user_pass).strip()

    def process_request(self, request, spider):
        PROXIES = [
            "http://root:woshiniba@192.168.11.11:9999/",
            "http://root:woshiniba@192.168.11.12:9999/",
            "http://root:woshiniba@192.168.11.13:9999/",
            "http://root:woshiniba@192.168.11.14:9999/",
            "http://root:woshiniba@192.168.11.15:9999/",
            "http://root:woshiniba@192.168.11.16:9999/",
        ]
        url = random.choice(PROXIES)

        orig_type = ""
        proxy_type, user, password, hostport = _parse_proxy(url)
        proxy_url = urlunparse((proxy_type or orig_type, hostport, '', '', '', ''))

        if user:
            creds = self._basic_auth_header(user, password)
        else:
            creds = None
        request.meta['proxy'] = proxy_url
        if creds:
            request.headers['Proxy-Authorization'] = b'Basic ' + creds


class DdbProxyMiddleware(object):
    def process_request(self, request, spider):
        PROXIES = [
            {'ip_port': '111.11.228.75:80', 'user_pass': ''},
            {'ip_port': '120.198.243.22:80', 'user_pass': ''},
            {'ip_port': '111.8.60.9:8123', 'user_pass': ''},
            {'ip_port': '101.71.27.120:80', 'user_pass': ''},
            {'ip_port': '122.96.59.104:80', 'user_pass': ''},
            {'ip_port': '122.224.249.122:8088', 'user_pass': ''},
        ]
        proxy = random.choice(PROXIES)
        if proxy['user_pass'] is not None:
            request.meta['proxy'] = to_bytes("http://%s" % proxy['ip_port'])
            encoded_user_pass = base64.b64encode(to_bytes(proxy['user_pass']))
            request.headers['Proxy-Authorization'] = to_bytes('Basic ' + encoded_user_pass)
        else:
            request.meta['proxy'] = to_bytes("http://%s" % proxy['ip_port'])

DOWNLOADER_MIDDLEWARES = {
   #'xdb.middlewares.XdbDownloaderMiddleware': 543,
    'xdb.proxy.XdbProxyMiddleware':751,
    'xdb.proxy.DdbProxyMiddleware':751,
}

 

scrapy 解析器

在程序中使用scrapy中的xpath

html = """<!DOCTYPE html>
<html>
    <head lang="en">
        <meta charset="UTF-8">
        <title></title>
    </head>
    <body>
        <ul>
            <li class="item-"><a id='i1' href="link.html">first item</a></li>
            <li class="item-0"><a id='i2' href="llink.html">first item</a></li>
            <li class="item-1"><a href="llink2.html">second item<span>vv</span></a></li>
        </ul>
        <div><a href="llink2.html">second item</a></div>
    </body>
</html>
"""

from scrapy.http import HtmlResponse
from scrapy.selector import Selector

response = HtmlResponse(url='http://example.com', body=html,encoding='utf-8')


# hxs = Selector(response)
# hxs.xpath()
response.xpath('')

 自定制命令

• 在spiders同级创建任意目录，如：commands
• 在其中创建 crawlall.py 文件 （此处文件名就是自定义的命令）

from scrapy.commands import ScrapyCommand
from scrapy.utils.project import get_project_settings


class Command(ScrapyCommand):

    requires_project = True

    def syntax(self):
        return '[options]'

    def short_desc(self):
        return 'Runs all of the spiders'

    def run(self, args, opts):
        spider_list = self.crawler_process.spiders.list()
        for name in spider_list:
            self.crawler_process.crawl(name, **opts.__dict__)
        self.crawler_process.start()

• 在settings.py 中添加配置 COMMANDS_MODULE = '项目名称.目录名称'

 

# 自定制命令目录
COMMANDS_MODULE  = "xdb.commands"

　　

• 在项目目录执行命令：scrapy crawlall 

 

import sys
from scrapy.cmdline import execute

if __name__ == '__main__':
    execute(["scrapy","github","--nolog"])