Python下載小說遮天

V1.0

---抓取的筆趣閣網站上的
---用的xpath解析html
---後邊的章節目錄爲啥不見了尷尬

---num參數爲下載多少章節

import requests
import unicodedata
from lxml import etree
headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0'
    }
num = 10  #下載多少章
first = 'https://www.bqg5.cc/1_1273/'
numfirst = 669621
last = '.html'
for i in range(0,num):
    url = first+str(numfirst+3*i)+last
    res = requests.get(url = url,headers=headers)
    if res.status_code==200:
        print('請求成功!')
        html = etree.HTML(res.text)
        data = html.xpath('/html/body/div[@id="wrapper"]/div[@class="content_read"]/div[@class="box_con"]/div[@id="content"]/p/text()')
        mystr = '\n'.join(data)
        print(mystr)
        if i==0:
            with open('C:/Users/lsy/Desktop/1.txt','w') as fp:
                fp.write(mystr)
        else:
            with open('C:/Users/lsy/Desktop/1.txt','a') as fp:
                fp.write(mystr)

V1.1

經過大神們的回覆，目前修復了章節不存在的bug,但是還是存在下載速度不夠快和下到了500多章後程序無響應這種異常情況

import requests
import unicodedata
from lxml import etree
headers = {
        'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:75.0) Gecko/20100101 Firefox/75.0'
    }
mulu_url = 'https://www.bqg5.cc/5_5157/'
main_url='https://www.bqg5.cc'
rep = requests.get(url = mulu_url,headers=headers)
if rep.status_code==200:
    print('請求目錄頁成功！')
    mulu_html = etree.HTML(rep.text)
    mulu_array= mulu_html.xpath('//div[@class="box_con"]//dl/dd/a/@href')
    num = len(mulu_array)   #章節一共有多少章
for i in range(9,num):
    #rint('i='+str(i))
    xiazai_url = main_url+mulu_array[i]
    #print(xiazai_url)
    res = requests.get(url = xiazai_url,headers=headers)
    if res.status_code==200:
        print('請求成功!')
        print('正在下載',i-8)
        html = etree.HTML(res.text)
        data = html.xpath('/html/body/div[@id="wrapper"]/div[@class="content_read"]/div[@class="box_con"]/div[@id="content"]/p/text()')
        mystr = '\n'.join(data)
        #print(mystr)
        if i==9:
            with open('C:/Users/lsy/Desktop/蠱真人1.txt','w') as fp:
                fp.write(mystr)
        else:
            with open('C:/Users/lsy/Desktop/蠱真人1.txt','a') as fp:
                fp.write(mystr)
    else:
        print('請求失敗！'+xiazai_url)