garden/soup.py

#!/usr/bin/env python3
import glob
import re
import urllib.parse
from collections import defaultdict
from bs4 import BeautifulSoup


UUID_PATTERN = "^[0-9a-f]{8}-[0-9a-f]{4}-[0-5][0-9a-f]{3}-[089ab][0-9a-f]{3}-[0-9a-f]{12}$"

def match_uuid(headline_id: str | None) ->bool:
    if headline_id is None:
        return False

    result = re.match(UUID_PATTERN, headline_id) # Returns Match object
    if result is None:
        return False

    return True


def get_node_link(node_contend: str):
    node_soup = BeautifulSoup(node_contend, "lxml")

    temp_link = node_soup.find_all(name='a',class_='internal-link')
    node_link = set()
    for i in temp_link:
        i = i.get("href")

        if i == "":
            continue

        node_link.add(i)
    return node_link


def new_section(soup):
    new_div = soup.new_tag("div")
    new_div["class"] = 'bl-section'
    new_h4 = soup.new_tag("h4")
    new_h4.string = "反向链接"
    new_div.append(new_h4)
    bl_ul = soup.new_tag("ul")
    new_div.append(bl_ul)

    return new_div


def soup_link():
    files = glob.glob("public/main/*/*.html")
    files += glob.glob("public/daily/*/*.html")
    files += glob.glob("public/references/*/*.html")
    files += glob.glob("public/articles/*/*.html")

    _pages_dict = defaultdict(dict)
    for file in files:
        with open(file, 'r') as f:
            soup = BeautifulSoup(f.read(), "lxml")

        temp_link = soup.find_all(name='a',class_='internal-link')
        page_link = set()
        for i in temp_link:
            i = i.get("href")
            page_link.add(i)

        _nodes = soup.find_all(["h1", "h2", "h3", "h4", "h5", "h6"])
        nodes = [i for i in _nodes if match_uuid(i.get("id"))]
        nodes_dict = {}
        file_name = file.split('/')[-2]

        for node in nodes:
            node_dict = {}
            node_element = node
            node_dict["name"] = node_element.contents[0]

            iii = node_element.find_next_sibling()
            node_content = ''
            while node_element.name != iii.name:
                node_content += str(iii)
                iii = iii.find_next_sibling()
                if iii == None:
                    break

            node_id_link =  '/' + file_name + '/#'  +node_element["id"]
            node_dict["links"] = get_node_link(node_content)
            node_dict["id-link"] = node_id_link
            node_dict["backlinks"] = []
            nodes_dict[node_element["id"]] = node_dict

        for i in nodes_dict:
            for node_link in nodes_dict[i]["links"]:
                if node_link in page_link:
                    page_link.remove(node_link)

        _pages_dict[file_name]["name"] = soup.title.string
        _pages_dict[file_name]["path"] = file
        _pages_dict[file_name]["links"] = page_link
        _pages_dict[file_name]["backlinks"] = []
        _pages_dict[file_name]["nodes"] = nodes_dict

    return _pages_dict


def build_backlinks_dict(pages_dict):
    backlinks_dict = pages_dict
    for page in pages_dict:
        for _link in pages_dict[page]["links"]:
            if _link == "":
                continue

            link = urllib.parse.unquote(_link).split("/")
            _filter = [
                i
                for i in backlinks_dict
                if backlinks_dict[i]["path"] == f"public/{link[-3]}/{link[-2]}/index.html"
            ]
            if len(_filter) == 0:
                continue

            post_link = re.findall(r"public(.*)index.html", pages_dict[page]["path"])[0]
            backlinks_dict[_filter[0]]["backlinks"].append(post_link)

        for node in pages_dict[page]["nodes"]:
            for node_link in pages_dict[page]["nodes"][node]["links"]:
                node_link = urllib.parse.unquote(node_link)
                node_link = node_link.split('/')

                if len(node_link) == 1:
                    link_node = node_link[0][1:]
                    node_link = '#' + node
                    backlinks_dict[page]["nodes"][link_node]["backlinks"].append(node_link)
                elif len(node_link) > 2:
                    # ['', 'posts', '卡片笔记写作法', '#卡片笔记中有哪些索引-p9']
                    if node_link[-2] == page:
                        link_node = link[-1][1:]
                        node_link = node_link[-1]
                        backlinks_dict[page]["nodes"][link_node]["backlinks"].append(node_link)
                    else:
                        if node_link[-1].startswith('#'):
                            link_page = node_link[-2]
                            link_node = node_link[-1][1:]
                            backlinks_dict[link_page]["nodes"][link_node]["backlinks"].append(pages_dict[page]["nodes"][node]["id-link"])
                        else:
                            link_page = node_link[-2]
                            backlinks_dict[link_page]["backlinks"].append(pages_dict[page]["nodes"][node]["id-link"])

    return backlinks_dict


def write_backlinks(backlinks_dict):
    def parse_page_backlinks(i):
        backlink_filename = i.split('/')[-2]
        backlink_nodename = i.split('/')[-1][1:]
        try:
            backlink_name = backlinks_dict[backlink_filename]["nodes"][backlink_nodename]["name"].rstrip()
        except KeyError:
            _filter = [
                x
                for x in backlinks_dict
                if backlinks_dict[x]["path"] == f"public{i}index.html"
            ][0]
            backlink_name = backlinks_dict[_filter]["name"]

        new_li = soup.new_tag("li")
        new_a = soup.new_tag("a", href=i)
        new_a.string = backlink_name
        new_li.append(new_a)

        bl_section = soup.find(class_="bl-section").find(name="ul")
        bl_section.append(new_li)


    def parse_node_backlink(i):
        new_bl = new_section(soup)
        for ii in backlinks_dict[page]["nodes"][i]["backlinks"]:
            link = ii.split("/")

            if link[-1].startswith("#"):
                backlink_nodename = link[0][1:]
                backlink_name = backlinks_dict[page]["nodes"][backlink_nodename][
                    "name"
                ].rstrip()

                # print(backlink_name)
            else:
                backlink_nodename = link[2]
                backlink_name = backlinks_dict[backlink_nodename]["name"].rstrip()
            # if len(link) > 1:
            #     backlink_pagename = link[2]
            #     backlink_nodename = link[3][1:]
            #     print(link)
            #     print(page)
            #     backlink_name = backlinks_dict[backlink_pagename]["nodes"][backlink_nodename][
            #         "name"
            #     ].rstrip()

            new_li = soup.new_tag("li")
            new_a = soup.new_tag("a", href=ii)
            new_a.string = backlink_name
            new_li.append(new_a)
            new_bl.append(new_li)

            bl_section = soup.find(id=i)
            iii = bl_section.find_next_sibling()
            heading = int(bl_section.name[1:])

            while (True):
                if iii.find_next_sibling() == None:
                    iii.append(new_bl)
                    break
                if iii.name.startswith('h') and (int(iii.name[1:]) <= heading):
                    iii.find_previous_sibling().append(new_bl)
                    break
                iii = iii.find_next_sibling()

    for page in backlinks_dict:
        try:
            with open(backlinks_dict[page]["path"], 'r') as f:
                soup = BeautifulSoup(f.read(), "lxml")
        except FileNotFoundError as e:
            print('except:', e)
            continue

        content_section = soup.find(class_="content")
        content_section.insert_after(new_section(soup))

        for i in backlinks_dict[page]["backlinks"]:
            parse_page_backlinks(i)
        for i in backlinks_dict[page]["nodes"]:
            if backlinks_dict[page]["nodes"][i]["backlinks"] == []:
                continue

            parse_node_backlink(i)

        with open(backlinks_dict[page]["path"], "w", encoding="utf-8") as f:
            f.write(str(soup))
            print("write " + page + '!')


pages_dict = soup_link()
backlinks_dict = build_backlinks_dict(pages_dict)
write_backlinks(backlinks_dict)