ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixed some bugs in robots.txt processing

Browse Source
This commit is contained in:
Aravind Karnam
2024-10-03 15:58:57 +05:30
parent 7fe220dbd5
commit d743adac68
1 changed files with 10 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
crawl4ai/scraper/bfs_scraper_strategy.py
View File

@@ -32,13 +32,17 @@ class BFSScraperStrategy(ScraperStrategy):
# Robots.txt Parser # Robots.txt Parser
def get_robot_parser(self, url: str) -> RobotFileParser: def get_robot_parser(self, url: str) -> RobotFileParser:
domain = urlparse(url).netloc domain = urlparse(url)
if domain not in self.robot_parsers: scheme = domain.scheme if domain.scheme else 'http' # Default to 'http' if no scheme provided
netloc = domain.netloc
if netloc not in self.robot_parsers:
rp = RobotFileParser() rp = RobotFileParser()
rp.set_url(f"https://{domain}/robots.txt") rp.set_url(f"{scheme}://{netloc}/robots.txt")
rp.read() rp.read()
self.robot_parsers[domain] = rp self.robot_parsers[netloc] = rp
return self.robot_parsers[domain] return self.robot_parsers[netloc]
# Retry with exponential backoff # Retry with exponential backoff
@retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10)) @retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10))
@@ -56,7 +60,7 @@ class BFSScraperStrategy(ScraperStrategy):
return None return None
# Robots.txt Compliance # Robots.txt Compliance
if not self.get_robot_parser(url).can_fetch("YourUserAgent", url): if not self.get_robot_parser(url).can_fetch(crawler.crawler_strategy.user_agent, url):
logging.info(f"Skipping {url} as per robots.txt") logging.info(f"Skipping {url} as per robots.txt")
return None return None