python 特别簡單的一個小爬蟲（看着玩吧 ）

  環境：python3.5    bs4   lxml這是需要安裝的

  使用urllib子產品來通路頁面 bs4解析頁面，存到*.txt檔案中

#-*-  coding:utf-8  -*-
import urllib.request
import time,os
import numpy as np

from bs4 import BeautifulSoup

hds=[{'User-Agent': 'Mozilla/5.0 (Windows; U;Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'}, \
     {'User-Agent': 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.12 Safari/535.11'}, \
     {'User-Agent': 'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Trident/6.0)'}]
def search(value,page):

    url='http://so.gushiwen.org/search.aspx?type=author&page='+urllib.request.quote(str(page))+'&value='+urllib.request.quote(value)
    #拼接url使用urllib.request.quote（）把漢字和數字拼接到url裡
    time.sleep(np.random.rand() * 3)#随機等一段時間再進行通路
    try:
        req=urllib.request.Request(url,headers=hds[page%3])
        html_resource=urllib.request.urlopen(req)
        # print(html_resource.info()) 輸出伺服器資訊
        plain_text=html_resource.read().decode()
        return plain_text

    except (urllib.request.HTTPError,urllib.request.URLError) as e:
        print(e)

def rmline(str):
    #這是一個去除字元串中的空行的函數
    data=''
    for line in str:
        l=line.strip()
        if len(l)!=0:
            data+=l
    return data

def parseHtml(html,page):

    # soup=BeautifulSoup(html,'lxml')
    # title=soup.title#擷取網頁title
    # title_name=title.name#擷取title的名字 也就是标簽的名字
    # title_string=title.string#擷取title的值
    # title_parent=soup.title.parent#title的父對象
    #
    # soup.p#擷取第一個p标簽
    # soup.p['class']#擷取第一個p标簽裡面的class值
    #
    # soup.find_all('a')#找到所有的a标簽
    # soup.find(id='***')#擷取id為***的标簽
    soup=BeautifulSoup(html,'lxml')
    with open('poem.txt',mode='a',encoding='utf-8') as f:
        f.write('第'+str(page)+'頁'+'\n')

    if page==1:
        for poem in soup.find_all("div", "sons")[1:]:
            poem_title = poem.p
            poem_title_str = poem_title.a.string
            poem_author = poem_title.next_sibling.next_sibling
            poem_author_str = poem_author.span.string
            poem_value = poem_author.next_sibling.next_sibling
            poem_value_str = list(poem_value.strings)[0]
            # 注意：.strings擷取的是generator它是疊代的。直接取值不好取，轉化成list再取值。

            with open('poem.txt', mode='a', encoding='utf-8') as f:
                f.write('題目： ' + rmline(poem_title_str)+'\n')
                f.write('作者： ' + poem_author_str+'\n')
                f.write('内容： ' + poem_value_str+'\n')
                f.write('-----------------------------------------'+'\n')

    else:
        for poem in soup.find_all("div", "sons"):
            poem_title = poem.p
            poem_title_str = poem_title.a.string
            poem_author = poem_title.next_sibling.next_sibling
            poem_author_str = poem_author.span.string
            poem_value = poem_author.next_sibling.next_sibling
            poem_value_str = list(poem_value.strings)[0]
            # 注意：.strings擷取的是generator它是疊代的。直接取值不好取，轉化成list再取值。

            with open('poem.txt', mode='a', encoding='utf-8') as f:
                f.write('題目： ' + rmline(poem_title_str)+'\n')
                f.write('作者： ' + poem_author_str+'\n')
                f.write('内容： ' + poem_value_str+'\n')
                f.write('-----------------------------------------'+'\n')




if __name__=="__main__":
    filename='poem.txt'
    if os.path.exists(filename):
        os.remove(filename)
    for page in range(1,4):
        #1，4是指頁數，也就是下載下傳前三頁資料。下面的作者名字可以随意改，或者寫詩的名字也可以
        parseHtml(search('納蘭性德',page), page)