Learn more  » Push, build, and install  RubyGems npm packages Python packages Maven artifacts PHP packages Go Modules Bower components Debian packages RPM packages NuGet packages

hemamaps / Scrapy   python

Repository URL to install this package:

Version: 1.1.1 

/ spiders / sitemap.py

import re
import logging
import six

from scrapy.spiders import Spider
from scrapy.http import Request, XmlResponse
from scrapy.utils.sitemap import Sitemap, sitemap_urls_from_robots
from scrapy.utils.gz import gunzip, is_gzipped

logger = logging.getLogger(__name__)


class SitemapSpider(Spider):

    sitemap_urls = ()
    sitemap_rules = [('', 'parse')]
    sitemap_follow = ['']
    sitemap_alternate_links = False

    def __init__(self, *a, **kw):
        super(SitemapSpider, self).__init__(*a, **kw)
        self._cbs = []
        for r, c in self.sitemap_rules:
            if isinstance(c, six.string_types):
                c = getattr(self, c)
            self._cbs.append((regex(r), c))
        self._follow = [regex(x) for x in self.sitemap_follow]

    def start_requests(self):
        for url in self.sitemap_urls:
            yield Request(url, self._parse_sitemap)

    def _parse_sitemap(self, response):
        if response.url.endswith('/robots.txt'):
            for url in sitemap_urls_from_robots(response.text):
                yield Request(url, callback=self._parse_sitemap)
        else:
            body = self._get_sitemap_body(response)
            if body is None:
                logger.warning("Ignoring invalid sitemap: %(response)s",
                               {'response': response}, extra={'spider': self})
                return

            s = Sitemap(body)
            if s.type == 'sitemapindex':
                for loc in iterloc(s, self.sitemap_alternate_links):
                    if any(x.search(loc) for x in self._follow):
                        yield Request(loc, callback=self._parse_sitemap)
            elif s.type == 'urlset':
                for loc in iterloc(s):
                    for r, c in self._cbs:
                        if r.search(loc):
                            yield Request(loc, callback=c)
                            break

    def _get_sitemap_body(self, response):
        """Return the sitemap body contained in the given response,
        or None if the response is not a sitemap.
        """
        if isinstance(response, XmlResponse):
            return response.body
        elif is_gzipped(response):
            return gunzip(response.body)
        elif response.url.endswith('.xml'):
            return response.body
        elif response.url.endswith('.xml.gz'):
            return gunzip(response.body)


def regex(x):
    if isinstance(x, six.string_types):
        return re.compile(x)
    return x


def iterloc(it, alt=False):
    for d in it:
        yield d['loc']

        # Also consider alternate URLs (xhtml:link rel="alternate")
        if alt and 'alternate' in d:
            for l in d['alternate']:
                yield l