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

Merge pull request #1448 from unclecode/fix/https-reditrect

Browse Source 
feat: add preserve_https_for_internal_links flag to maintain HTTPS during crawling
This commit is contained in:
Nasrin
2025-09-01 16:11:25 +08:00
committed by GitHub
parent 2de200c1ba bdacf61ca9
commit 5e7fcb17e1
8 changed files with 246 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
crawl4ai/async_configs.py
View File

@@ -1124,6 +1124,7 @@ class CrawlerRunConfig():
exclude_domains: list = None,
exclude_internal_links: bool = False,
score_links: bool = False,
preserve_https_for_internal_links: bool = False,
# Debugging and Logging Parameters
verbose: bool = True,
log_console: bool = False,
@@ -1247,6 +1248,7 @@ class CrawlerRunConfig():
self.exclude_domains = exclude_domains or []
self.exclude_internal_links = exclude_internal_links
self.score_links = score_links
self.preserve_https_for_internal_links = preserve_https_for_internal_links
# Debugging and Logging Parameters
self.verbose = verbose
@@ -1520,6 +1522,7 @@ class CrawlerRunConfig():
exclude_domains=kwargs.get("exclude_domains", []),
exclude_internal_links=kwargs.get("exclude_internal_links", False),
score_links=kwargs.get("score_links", False),
preserve_https_for_internal_links=kwargs.get("preserve_https_for_internal_links", False),
# Debugging and Logging Parameters
verbose=kwargs.get("verbose", True),
log_console=kwargs.get("log_console", False),
@@ -1626,6 +1629,7 @@ class CrawlerRunConfig():
"exclude_domains": self.exclude_domains,
"exclude_internal_links": self.exclude_internal_links,
"score_links": self.score_links,
"preserve_https_for_internal_links": self.preserve_https_for_internal_links,
"verbose": self.verbose,
"log_console": self.log_console,
"capture_network_requests": self.capture_network_requests,

2
crawl4ai/async_webcrawler.py
View File

@@ -354,6 +354,7 @@ class AsyncWebCrawler:
###############################################################
# Process the HTML content, Call CrawlerStrategy.process_html #
###############################################################
from urllib.parse import urlparse
crawl_result: CrawlResult = await self.aprocess_html(
url=url,
html=html,
@@ -364,6 +365,7 @@ class AsyncWebCrawler:
verbose=config.verbose,
is_raw_html=True if url.startswith("raw:") else False,
redirected_url=async_response.redirected_url,
original_scheme=urlparse(url).scheme,
**kwargs,
)

6
crawl4ai/content_scraping_strategy.py
View File

@@ -258,7 +258,11 @@ class LXMLWebScrapingStrategy(ContentScrapingStrategy):
continue
try:
normalized_href = normalize_url(href, url)
normalized_href = normalize_url(
href, url,
preserve_https=kwargs.get('preserve_https_for_internal_links', False),
original_scheme=kwargs.get('original_scheme')
)
link_data = {
"href": normalized_href,
"text": link.text_content().strip(),

41
crawl4ai/utils.py
View File

@@ -2146,7 +2146,9 @@ def normalize_url(
drop_query_tracking=True,
sort_query=True,
keep_fragment=False,
extra_drop_params=None
extra_drop_params=None,
preserve_https=False,
original_scheme=None
):
"""
Extended URL normalizer
@@ -2176,6 +2178,17 @@ def normalize_url(
# Resolve relative paths first
full_url = urljoin(base_url, href.strip())
# Preserve HTTPS if requested and original scheme was HTTPS
if preserve_https and original_scheme == 'https':
parsed_full = urlparse(full_url)
parsed_base = urlparse(base_url)
# Only preserve HTTPS for same-domain links (not protocol-relative URLs)
# Protocol-relative URLs (//example.com) should follow the base URL's scheme
if (parsed_full.scheme == 'http' and
parsed_full.netloc == parsed_base.netloc and
not href.strip().startswith('//')):
full_url = full_url.replace('http://', 'https://', 1)
# Parse once, edit parts, then rebuild
parsed = urlparse(full_url)
@@ -2227,7 +2240,7 @@ def normalize_url(
return normalized
def normalize_url_for_deep_crawl(href, base_url):
def normalize_url_for_deep_crawl(href, base_url, preserve_https=False, original_scheme=None):
"""Normalize URLs to ensure consistent format"""
from urllib.parse import urljoin, urlparse, urlunparse, parse_qs, urlencode
@@ -2238,6 +2251,17 @@ def normalize_url_for_deep_crawl(href, base_url):
# Use urljoin to handle relative URLs
full_url = urljoin(base_url, href.strip())
# Preserve HTTPS if requested and original scheme was HTTPS
if preserve_https and original_scheme == 'https':
parsed_full = urlparse(full_url)
parsed_base = urlparse(base_url)
# Only preserve HTTPS for same-domain links (not protocol-relative URLs)
# Protocol-relative URLs (//example.com) should follow the base URL's scheme
if (parsed_full.scheme == 'http' and
parsed_full.netloc == parsed_base.netloc and
not href.strip().startswith('//')):
full_url = full_url.replace('http://', 'https://', 1)
# Parse the URL for normalization
parsed = urlparse(full_url)
@@ -2275,7 +2299,7 @@ def normalize_url_for_deep_crawl(href, base_url):
return normalized
@lru_cache(maxsize=10000)
def efficient_normalize_url_for_deep_crawl(href, base_url):
def efficient_normalize_url_for_deep_crawl(href, base_url, preserve_https=False, original_scheme=None):
"""Efficient URL normalization with proper parsing"""
from urllib.parse import urljoin
@@ -2285,6 +2309,17 @@ def efficient_normalize_url_for_deep_crawl(href, base_url):
# Resolve relative URLs
full_url = urljoin(base_url, href.strip())
# Preserve HTTPS if requested and original scheme was HTTPS
if preserve_https and original_scheme == 'https':
parsed_full = urlparse(full_url)
parsed_base = urlparse(base_url)
# Only preserve HTTPS for same-domain links (not protocol-relative URLs)
# Protocol-relative URLs (//example.com) should follow the base URL's scheme
if (parsed_full.scheme == 'http' and
parsed_full.netloc == parsed_base.netloc and
not href.strip().startswith('//')):
full_url = full_url.replace('http://', 'https://', 1)
# Use proper URL parsing
parsed = urlparse(full_url)