【哑舍】章节目录爬取

import requests
from bs4 import BeautifulSoup
url='https://www.manhuatai.com/yashe/?_t_t_t=0.09846753146736842'
r=requests.get(url)
r.raise_for_status()
r.encoding=r.apparent_encoding
txt=r.text
soup=BeautifulSoup(txt,'html.parser')
ls=[]
for item in soup.find_all('a'):
ls.append(item)
print(ls)

1.源代码奉上；

由于漫客平台限制网络爬取功能，所以找的是漫画台版本，进行目录，以及部分章节图片的爬取。

import requests
import json
import urllib

def getSogouImag(category,length,path):
    n = length
    cate = category
    imgs = requests.get('http://pic.sogou.com/pics/channel/getAllRecomPicByTag.jsp?category='+cate+'&tag=%E5%85%A8%E9%83%A8&start=0&len='+str(n))
    jd = json.loads(imgs.text)
    jd = jd['all_items']
    imgs_url = []
    for j in jd:
        imgs_url.append(j['bthumbUrl'])
    m = 0
    for img_url in imgs_url:
            print('***** '+str(m)+'.jpg *****'+'   Downloading...')
            urllib.request.urlretrieve(img_url,path+str(m)+'.jpg')
            m = m + 1
    print('Download complete!')

getSogouImag('壁纸',2000,'C:/User/每天无敌帅/Local/Programs/Magic/Magic(1)(1)/download/壁纸/')