Python爬虫之爬取最新更新的小说网站

https://www.baidu.com/s?wd=搜索词&pn=10&rn=50

<h3 class="t"><a data-click="{
			'F':'778317EA',
			'F1':'9D73F1E4',
			'F2':'4CA6DE6B',
			'F3':'54E5243F',
			'T':'1620130755',
			'y':'FE7FF57A'}" 
			href="http://www.baidu.com/link?url=9LLa46B6hp69vJdLx6wOGfBpoS7BaRe8zV3oSNj_Vc2AxuU0Tz5Bl7CZlqNPobdw_BElAgaadA_HfCJMtADpyq" rel="external nofollow"  target="_blank">
			<em>青萍</em>最新章节,<em>青萍</em>免费阅读 - 大神小说网</a>
			</h3>

<p>最新章节：<a href="/book/12/12938/358787.html" rel="external nofollow"  target="_blank">第729章 就是给你们看看的</a></p>

def getHostName(url):
    httpPost = url[10:]
    hostName = url[:10]+httpPost.split('/')[0]
    return hostName

def getNoteInfo(url):
    """
    打开指定小说网页URL获取最新章节信息
    url:百度搜索结果指定的搜索匹配记录的url
    返回该URL对应的章节ID、打开耗时、网站真正URL、网站主机名、章节相对url、章节名
    
    """
    head = mkhead()
    start = time.time_ns()
    req = urllib.request.Request(url=url, headers=head)
    try:
        resp = urllib.request.urlopen(req,timeout=2)
        #根据响应头获取真正的网页URL对应的网站名
        hostName = getHostName(resp.url)
        text = resp.read()
        #网页编码有2种：utf-8和GBK
        pageText = text.decode('utf-8')
    except UnicodeDecodeError:
        pageText =  text.decode('GBK')
    except Exception as  e:
        errInf = f"打开网站 {url} 失败，异常原因：\n{e}\n" + '\n' + traceback.format_exc() + '\n'
        logPag(errInf, False)
        return None

    #最新章节的HTML报文类似： '<p>最新章节：<a href="/html/107018/122306672.html" rel="external nofollow" >第672章 天之关梁</a></p>'
    end = time.time_ns()
    soup = BeautifulSoup(pageText, 'lxml')
    # 根据最新章节的提示信息搜索最新章节
    result = soup.find_all(string=re.compile(r'最新更新[：:]|最新章节[：:]|最近更新[：:]|最新[：:]'))
    found = False
    for rec in result:
        recP = rec.parent
        pa = recP.a
        matchs = re.match(r'(?:最新更新|最新章节|最近更新|最新)[：:]第(.+)章(.+)', recP.text)
        if not matchs:return None
        groups = matchs.groups()
        if matchs and pa is not None:
            found = True
            chapter = toInt(groups[0]) #章节序号
            chapterName = groups[1] #章节名
            chaperUrl = pa.attrs['href'] #章节相对URL
            break
    if not found:
        return None

    cost = (end - start) / 1000000  #网页打开耗时计算
    return (chapter,cost,resp.url,hostName,chaperUrl,chapterName)

def getChapterUrl(noteInf):
    chapter, cost, url, hostName, chaperUrl, chapterName = noteInf
    if chaperUrl.strip().startswith('http'):return chaperUrl
    elif chaperUrl.strip().startswith('/'):return hostName.strip()+chaperUrl.strip()
    else:return hostName.strip()+'/'+chaperUrl.strip()

def noteWeight(n):
#入参n为小说信息元组: chapter, cost, url, hostName, chaperUrl, chapterName
    ch,co = n[:2]
    w = ch * 100000 + min(99999, 100000 / co)
    return w

def BDSearchUsingChrome(inputword,maxCount=150):
    """
    输出相关搜索结果中具有最新章节且访问速度最快的前5个网站url
    :param word: 搜索关键词，如小说名、小说名+作者名等
    :param maxCount: 最多处理的搜索记录数
    :return: None
    """
    #百度请求url类似：https://www.baidu.com/s?wd=青萍&pn=10&rn=50
    rn = 50 #每页50条记录
    #构建请求头模拟本机谷歌浏览器访问百度网页
    head = mkheadByHostForChrome('baidu.com')
    word =  urllib.parse.quote(inputword)
    urlPagePre = 'https://www.baidu.com/s?wd='+word+'&rn=50&'
    pageCount = int(0.999+maxCount/rn)
    validNoteInf = []
    seq = 0
    logPag("开始执行搜索...")
    for page in range(pageCount):
        pn = rn*page
        urlPage = urlPagePre+str(pn)
        pageReq = urllib.request.Request(url=urlPage, headers=head)
        pageResp = urllib.request.urlopen(pageReq,timeout=2)
        pageText = pageResp.read().decode()

        if pageResp.status == 200:
            soup = BeautifulSoup(pageText,'lxml')
            links = soup.select('h3.t a[href^="http://www.baidu.com/link?url="]')

            for l in links:
                noteInf = getNoteInfo(l.attrs['href'])
                seq += 1
                if noteInf is None:
                    #print(seq,'、',l.attrs['href'],None)
                    logPag(f"{seq}、{l.attrs['href']}:查找最新章节失败，忽略",True)
                else:
                    logPag(f"{seq}、返回小说信息： {noteInf}",True)
                    #chapter,cost,url,hostName,chaperUrl,chapterName = noteInf
                    validNoteInf.append(noteInf)
    validNoteInf.sort(key=noteWeight,reverse=True)
    print(f"小说： {inputword} 最新更新访问最快的5个网站是：")
    for l in validNoteInf[:5]:#输出相关搜索结果中具有最新章节且访问速度最快的前5个网站url
        print(f"{validNoteInf.index(l)+1}、第{l[0]}章 {l[-1]}  {getChapterUrl(l)}  ，网页打开耗时 {l[1]} 毫秒")
    input("按回车键退出！")

BDSearchUsingChrome('青萍月关',150)