{"id":67623,"date":"2020-04-17T17:15:12","date_gmt":"2020-04-17T09:15:12","guid":{"rendered":"http:\/\/4563.org\/?p=67623"},"modified":"2020-04-17T17:15:12","modified_gmt":"2020-04-17T09:15:12","slug":"%e9%9a%94%e5%a3%81%e7%9c%8b%e5%88%b0%e7%9a%84%e7%88%ac%e8%99%ab%e4%b8%8b%e5%b0%8f%e8%af%b4python","status":"publish","type":"post","link":"http:\/\/4563.org\/?p=67623","title":{"rendered":"\u9694\u58c1\u770b\u5230\u7684\u722c\u866b\u4e0b\u5c0f\u8bf4[Python]"},"content":{"rendered":"\n

\t\t\t\t\thdwan.net<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

\u9694\u58c1\u770b\u5230\u7684\u722c\u866b\u4e0b\u5c0f\u8bf4[Python]<\/h3>\n

\t\timport requests                              #\u5bfc\u5165HTTP\u8bf7\u6c42\u5e93
from pyquery import PyQuery                        #PyQuery\uff0c\u539f\u751fcss\u9009\u62e9\u5668<\/p>\n

”’\u83b7\u53d6\u5355\u7ae0\u8282\u5185\u5bb9”’
def get_one_chapter(chapter_url = None, name = None):
    response = requests.get(url = chapter_url)
    doc = PyQuery(response.text)
    title = doc("h1").text()                            #\u201ch1\u201d\u5404\u7f51\u7ad9\u6807\u7b7e\u4e0d\u5c3d\u76f8\u540c\uff0c\u8bf7\u81ea\u884c\u5206\u6790\u7f51\u7ad9\u6e90\u7801\u914d\u7f6e
    content = doc("#content").text()                  #\u201c#content\u201d\u5404\u7f51\u7ad9\u5c0f\u8bf4\u5185\u5bb9\u5173\u952e\u8bcd\uff0c\u8bf7\u81ea\u884c\u5206\u6790\u7f51\u7ad9\u6e90\u7801\u914d\u7f6e
    print(title,content)
    with open(file = name + ".txt", mode = "a+", encoding = "utf-8") as f:
      f.write(title + "nn" + content)<\/p>\n

”’\u89e3\u6790\u4e00\u672c\u4e66\u6240\u6709\u7ae0\u8282\u7684url\u548c\u4e66\u540d”
def get_index(book_url):
    index_url = book_url
    text = requests.get(url = index_url).text
    doc = PyQuery(text)
    links = doc(‘#list a’)                                                      #links \u83b7\u53d6\u6240\u6709\u94fe\u63a5\u6807\u7b7e
    name = doc(‘h1’).text()
    for link in list(links.items()):                            #\u4e00\u822c\u76ee\u5f55\u7f51\u9875\u90fd\u4f1a\u6709\u9650\u663e\u793a\u6700\u65b0\u66f4\u65b0\u7ae0\u8282\uff0c\u66f4\u5177\u5b9e\u9645\u60c5\u51b5\u8df3\u8fc7\u7ae0\u8282
      chapter_url = ‘http:\/\/www.XXXXXX’ + link.attr.href            #\u9632\u6b62\u6709\u4eba\u8bf4\u6211\u6253\u5e7f\u544a\uff0c\u7f51\u5740\u81ea\u5df1\u914d\u7f6e
      get_one_chapter(chapter_url = chapter_url, name = name)<\/p>\n

”’\u89e3\u6790\u5168\u7ad9\u4e66\u7c4durl”’
def get_all_book_url():
    all_book_url = "http:\/\/www.XXXXXX"
    response = requests.get(url = all_book_url).text
    doc = PyQuery(response)
    links = doc(‘#main a’)
    for link in list(links.items()):
      book_url = ‘http:\/\/www.XXXXXX’ + link.attr.href
      get_index(book_url = book_url)<\/p>\n

get_all_book_url()<\/p>\n

https:\/\/www.vxotu.com\/u\/20200416\/1524233.png\t\t\t\t<\/p>\n

\t\t\t\t\ttir<\/strong> \t\t\t\t\u5927\u4f6c\u6709\u8bdd\u8bf4 : \t<\/p>\n

<\/h3>\n

\t\t\u770b\u8d77\u6765\u4e0d\u9519\uff0c\u4f46\u662f\u73b0\u5728\u4e0d\u9700\u8981\u722c\uff0c\u6709\u73b0\u6210\u7684\u89c4\u5219\t\t\t <\/p>\n","protected":false},"excerpt":{"rendered":"

hdwan.net \u5927\u4f6c\u6709\u8bdd\u8bf4 :…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[],"tags":[],"_links":{"self":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/67623"}],"collection":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=67623"}],"version-history":[{"count":0,"href":"http:\/\/4563.org\/index.php?rest_route=\/wp\/v2\/posts\/67623\/revisions"}],"wp:attachment":[{"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=67623"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=67623"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/4563.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=67623"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}