python 深度优先与广度优先

深度优先搜索算法（英语：Depth-First-Search，简称DFS）是一种用于遍历或搜索树或图的算法。 沿着树的深度遍历树的节点，尽可能深的搜索树的分支。当节点v的所在边都己被探寻过或者在搜寻时结点不满足条件，搜索将回溯到发现节点v的那条边的起始节点。整个进程反复进行直到所有节点都被访问为止。

import requests
from lxml import etree
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36'
}
#深度优先类
class DFS():
#	属性
    def __init__(self):
#    1. 容器
        self.dfs = []
        self.crawled = []
#    方法
#    1. 存
    def save_url(self,url):
        if url not in self.crawled:
            self.dfs.append(url)

#    2. 取
    def get_url(self):
        url = self.dfs.pop()
        self.crawled.append(url)
        return url

class Crawl():
    def __init__(self):
        self.dfs = DFS()


    def crawler(self):
        url = 'http://www.xbiquge.la/'
        self.dfs.save_url(url)
        while True:
            try:
                new_url = self.dfs.get_url()
                print(new_url)
                res = requests.get(url=new_url, headers=headers,timeout=3)
                ele = etree.HTML(res.content.decode())
                urls = ele.xpath("//a/@href")
                print(ele.xpath("//title/text()"))
                for i in urls:
                    if self.check_url(i):
                        self.dfs.save_url(i)
                print(self.dfs.dfs)
            except:
                pass

    def check_url(self,url):
        if (url.startswith('http://') or url.startswith('https://')) and not url.endswith('.exe'):
            return True
        else:
            return False


if __name__ == '__main__':
    crawl = Crawl()
    crawl.crawler()

宽度优先搜索算法（又称广度优先搜索）是最简便的图的搜索算法之一，这一算法也是很多重要的图的算法的原型。Dijkstra单源最短路径算法和Prim最小生成树算法都采用了和宽度优先搜索类似的思想。其别名又叫BFS，属于一种盲目搜寻法，目的是系统地展开并检查图中的所有节点，以找寻结果。换句话说，它并不考虑结果的可能位置，彻底地搜索整张图，直到找到结果为止。

import requests
from lxml import etree
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.70 Safari/537.36'
}
#广度优先类
class BFS():
#	属性
    def __init__(self):
#    1. 容器
        self.bfs = []
        self.crawled = []
#    方法
#    1. 存
    def save_url(self,url):
        if url not in self.crawled:
            self.bfs.append(url)

#    2. 取
    def get_url(self):
        url = self.bfs.pop(0)
        self.crawled.append(url)
        return url

class Crawl():
    def __init__(self):
        self.bfs = BFS()


    def crawler(self):
        url = 'http://www.baidu.com'
        self.bfs.save_url(url)
        while True:
            try:
                new_url = self.bfs.get_url()
                print(new_url)
                res = requests.get(url=new_url, headers=headers,timeout=3)
                ele = etree.HTML(res.content.decode())
                urls = ele.xpath("//a/@href")
                print(ele.xpath("//title/text()"))
                for i in urls:
                    if self.check_url(i):
                        self.bfs.save_url(i)
                print(self.bfs.bfs)
            except:
                pass

    def check_url(self,url):
        if (url.startswith('http://') or url.startswith('https://')) and not url.endswith('.exe'):
            return True
        else:
            return False


if __name__ == '__main__':
    crawl = Crawl()
    crawl.crawler()