Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: 修复fork抓取不全 #1563 #1565

Closed
wants to merge 2 commits into from
Closed

fix: 修复fork抓取不全 #1563 #1565

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
da63756
fix: 修复fork抓取不全 #1563
saurlax Nov 6, 2024
49caafb
fix: 修复fork中构造子链接的逻辑
saurlax Nov 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 18 additions & 9 deletions apps/common/util/fork.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,10 +25,10 @@ def __init__(self, base_url: str, selector_list: List[str]):
self.selector_list = selector_list

def fork(self, level: int, exclude_link_url: Set[str], fork_handler):
self.fork_child(ChildLink(self.base_url, None), self.selector_list, level, exclude_link_url, fork_handler)
self.fork_child(ChildLink(self.base_url, None), self.base_url, self.selector_list, level, exclude_link_url, fork_handler)

@staticmethod
def fork_child(child_link: ChildLink, selector_list: List[str], level: int, exclude_link_url: Set[str],
def fork_child(child_link: ChildLink, root_url: str, selector_list: List[str], level: int, exclude_link_url: Set[str],
fork_handler):
if level < 0:
return
Expand All @@ -37,12 +37,12 @@ def fork_child(child_link: ChildLink, selector_list: List[str], level: int, excl
child_url = child_link.url[:-1] if child_link.url.endswith('/') else child_link.url
if not exclude_link_url.__contains__(child_url):
exclude_link_url.add(child_url)
response = Fork(child_link.url, selector_list).fork()
response = Fork(child_link.url, root_url, selector_list).fork()
fork_handler(child_link, response)
for child_link in response.child_link_list:
child_url = child_link.url[:-1] if child_link.url.endswith('/') else child_link.url
if not exclude_link_url.__contains__(child_url):
ForkManage.fork_child(child_link, selector_list, level - 1, exclude_link_url, fork_handler)
ForkManage.fork_child(child_link, root_url, selector_list, level - 1, exclude_link_url, fork_handler)


def remove_fragment(url: str) -> str:
Expand All @@ -68,7 +68,7 @@ def success(html_content: str, child_link_list: List[ChildLink]):
def error(message: str):
return Fork.Response('', [], 500, message)

def __init__(self, base_fork_url: str, selector_list: List[str]):
def __init__(self, base_fork_url: str, root_url: str, selector_list: List[str]):
base_fork_url = remove_fragment(base_fork_url)
self.base_fork_url = urljoin(base_fork_url if base_fork_url.endswith("/") else base_fork_url + '/', '.')
parsed = urlsplit(base_fork_url)
Expand All @@ -81,13 +81,22 @@ def __init__(self, base_fork_url: str, selector_list: List[str]):
self.base_url = ParseResult(scheme=self.urlparse.scheme, netloc=self.urlparse.netloc, path='', params='',
query='',
fragment='').geturl()
self.root_url = root_url

def get_child_link_list(self, bf: BeautifulSoup):
pattern = "^((?!(http:|https:|tel:/|#|mailto:|javascript:))|" + self.base_fork_url + "|/).*"
pattern = "^((?!(http:|https:|tel:/|#|mailto:|javascript:))|" + self.root_url + "|/).*"
link_list = bf.find_all(name='a', href=re.compile(pattern))
result = [ChildLink(link.get('href'), link) if link.get('href').startswith(self.base_url) else ChildLink(
self.base_url + link.get('href'), link) for link in link_list]
result = [row for row in result if row.url.startswith(self.base_fork_url)]
result = []
for link in link_list:
if link.get('href').startswith("/"):
urlparsed = urlparse(self.root_url)
parsed_root_url = ParseResult(scheme=urlparsed.scheme, netloc=urlparsed.netloc, path='', params='', query='',
fragment='').geturl()
result.append(ChildLink(urljoin(parsed_root_url, link.get('href')), link))
elif link.get('href').startswith(self.root_url):
result.append(ChildLink(link.get('href'), link))
else:
result.append(ChildLink(self.base_url + link.get('href'), link))
return result

def get_content_html(self, bf: BeautifulSoup):
Expand Down
Loading