MCPcopy Create free account
hub / github.com/apify/crawlee-python / parse_sitemaps

Method parse_sitemaps

src/crawlee/_utils/robots.py:128–140  ·  view source on GitHub ↗

Parse the sitemaps from the robots.txt file and return a `Sitemap` instance. Args: enqueue_strategy: Forwarded to `get_sitemaps`; see that method for details.

(self, *, enqueue_strategy: EnqueueStrategy)

Source from the content-addressed store, hash-verified

126 return int(crawl_delay) if crawl_delay is not None else None
127
128 async def parse_sitemaps(self, *, enqueue_strategy: EnqueueStrategy) -> Sitemap:
129 """Parse the sitemaps from the robots.txt file and return a `Sitemap` instance.
130
131 Args:
132 enqueue_strategy: Forwarded to `get_sitemaps`; see that method for details.
133 """
134 sitemaps = self.get_sitemaps(enqueue_strategy=enqueue_strategy)
135 if not self._http_client:
136 raise ValueError('HTTP client is required to parse sitemaps.')
137
138 return await Sitemap.load(
139 sitemaps, self._http_client, self._proxy_info, parse_sitemap_options={'enqueue_strategy': enqueue_strategy}
140 )
141
142 async def parse_urls_from_sitemaps(self, *, enqueue_strategy: EnqueueStrategy) -> list[str]:
143 """Parse the sitemaps in the robots.txt file and return a list URLs.

Callers 1

Calls 2

get_sitemapsMethod · 0.95
loadMethod · 0.45

Tested by

no test coverage detected