python3爬蟲-快速入門-爬取圖片和標題

直接上代碼，先來個爬取豆瓣圖片的，大致思路就是發送請求-得到響應數據-儲存數據，原理的話可以先看看這個

https://www.cnblogs.com/sss4/p/7809821.html

import os#同來創造文件夾
import requests#發送請求和得到響應用的
from bs4 import BeautifulSoup#用來解析回應的數據

def GetHtmlText(url):#得到響應數據
    try:
        r = requests.get(url)#發送url
        r.raise_for_status()#判斷是否成功
        r.encoding = 'utf-8'#設置編碼格式
        return r.text#返回他的響應數據
    except:
        return ''
def main(pages):
    filepath=os.getcwd()+'\爬的圖片\\'#創造一個文件夾
    if not os.path.exists(filepath):#如果沒有則創造
        os.makedirs(filepath)

    pagenum=pages#要爬取的頁數
    fnum=1
    for page in range(pages):
        url="https://movie.douban.com/celebrity/1048000/photos/?type=C&start="+str(page*30)+'&sortby=like&size=a&subtype=a'#第幾頁
        html=GetHtmlText(url)
        soup=BeautifulSoup(html,'html.parser')#html。parser是解析器
        uls=soup.find_all('ul',class_="poster-col3 clearfix")#從響應的數據中找到ul class是xxxx的數據
        for ul in uls:
            imgs=ul.find_all('img') #找到img的標簽
            for img in imgs:
                imgurl=img['src']#得到img的url
                imgcontent=requests.get(imgurl).content#得到這個url下的內容content，應該是二進位的
                filename=str(fnum)+'.jpg'
                with open(filepath+filename,'wb') as wf:#二進位形式寫入數據
                    wf.write(imgcontent)
                fnum+=1


if __name__ == '__main__':
    main(9)

再來個爬去標題類的

import requests
from bs4 import BeautifulSoup

url="http://www.jianshu.com"
headers={'User-Agent':'SE 2.X MetaSr 1.0'}#設置請求頭的User-Agent，理解的話可以認為是從哪個瀏覽器發出的，不然的話會被反爬蟲
page=requests.get(url=url,headers=headers)
page_info=page.text
page_bf=BeautifulSoup(page_info,'html.parser')

#print(page_bf.prettify())
titles=page_bf.find_all('a','title')

for title in titles:
    print(title.string)
    print('http://www.jianshu.com'+title.get('href'))
with open(r"D:\untitled\爬蟲爬到的標題.txt","w",encoding='utf-8') as file:
    for title in titles:
        file.write(title.string+'\n')
        file.write("http://www.jianshu.com"+title.get('href')+'\n\n')

這個是下載小說的---（別人的代碼）

from bs4 import BeautifulSoup
import requests,sys
class downloader(object):
    def __init__(self):
        self.server="http://www.biqukan.com/"
        self.target="http://www.biqukan.com/1_1094"
        self.name=[]
        self.urls=[]
        self.nums=0

    def get_download_url(self):
        req=requests.get(url=self.target)
        html=req.text
        div_bf=BeautifulSoup(html)
        div=div_bf.find_all('div',class_='listmain')
        a_bf=BeautifulSoup(str(div[0]))
        a=a_bf.find_all('a')
        self.nums=len(a[15:])
        for each in a[15:]:
            self.name.append(each.string)
            self.urls.append(self.server+each.get('href'))
    def get_contents(self ,target):
        req=requests.get(url=target)
        html=req.text
        bf=BeautifulSoup(html)
        texts=bf.find_all('div',class_='showtxt')
        texts=texts[0].text.replace('\xa0'*8,'\n\n')
        return texts
    def writer(self,name,path,text):
        write_flag=True
        with open(path,"a",encoding='utf-8') as f:
            f.write(name+'\n')
            f.writelines(text)
            f.write('\n\n')

dl=downloader()
dl.get_download_url()
print("開始下載")
for i in range(dl.nums):
    dl.writer(dl.name[i], '一念永恆.txt', dl.get_contents(dl.urls[i]))
    sys.stdout.write("  已下載:%.3f%%" %  float(i/dl.nums) + '\r')
    sys.stdout.flush()
print('《一年永恆》下載完成')