学校-爬虫

爬取小说

import requests
from lxml import etree
url = 'https://www.xbiquge.la/xiaoshuodaquan/'
res = requests.get(url=url)
# print(res.text)
# 构建element对象
ele = etree.HTML(res.text)
# 对element对象进行xpath解析
book_names = ele.xpath("//div[@class='novellist']/ul/li/a/text()")
book_urls = ele.xpath("//div[@class='novellist']/ul/li/a/@href")
for book_index,book_url in enumerate(book_urls):
    res = requests.get(url=book_url)

    res = res.content.decode('utf-8')
    ele = etree.HTML(res)
    chapter_names = ele.xpath("//div[@id='list']/dl/dd/a/text()")
    chapter_urls = ele.xpath("//div[@id='list']/dl/dd/a/@href")
    print(chapter_urls)
    #https://www.xbiquge.la/15/15409/8163818.html
    urlTop = 'https://www.xbiquge.la'
    for chapter_index,chapter_url in enumerate(chapter_urls):
        chapter_url = urlTop+chapter_url
        print('网址是：'+chapter_url)
        res = requests.get(url=chapter_url)
        res = res.content.decode('utf-8')
        ele = etree.HTML(res)
        book_content = ele.xpath("//div[@id='content']/text()")

        s=chapter_names[chapter_index]+'\n'

        for i in book_content:
            s += i
            s +='\n'

        print('正在爬虫《'+book_names[book_index]+"》的"+chapter_names[chapter_index])
        print(s)
        with open(book_names[book_index]+'.txt','a+',encoding='utf-8')as w:
             w.write(s)
    break

网上的爬取sogou图片

import requests
import json
import urllib

def getSogouImag(category,length,path):
    n = length #个数
    cate = category  #类别
    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') #用于下载指定的url到本地
            m = m + 1
    print('Download complete!')

getSogouImag('壁纸',2000,'d:/download/壁纸/')

未完成的爬取sogou图片

import requests
import json
import urllib
from lxml import etree


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))
    # # print('imgs',imgs)
    # jd = json.loads(imgs.text)
    # # print('jd:',jd)
    # jd = jd['all_items']

    imgss_url = []
    for i in range(100):
        i=i+1
        url='https://pic.sogou.com/d?query=%E5%A3%81%E7%BA%B8&forbidqc=&entityid=&preQuery=&rawQuery=&queryList=&st=&mode=13&cwidth=1920&cheight=1080&dm=4&did='+str(i)
        imgss_url.append(url)
    imgs_url = []
    for url in imgss_url:
        # print('xxxx',url)
        res = requests.get(url)
        # print(res.text)
        ele = etree.HTML(res.text)
        imgurl = ele.xpath("//div[@class='img-box']/a/@href")
        print(imgurl)
        imgs_url.append(imgurl)

        break
    m = 0
    print(imgs_url)
    # for img_url in imgs_url:
    #         print('***** '+str(m)+'.jpg *****'+'   Downloading...')
    #         urllib.request.urlretrieve(img_url,path+str(m)+'.jpg') #用于下载指定的url到本地
    #         m = m + 1
    print('Download complete!')

getSogouImag('壁纸',2000,'d:/download/壁纸/')