分享一個能爬取全部百度貼吧圖片採集的代碼

代碼是用python3.x寫的.運行直接輸入貼吧名就能夠爬取圖片!

    例: 爬取 美女吧   直接輸入: 美女

爬取完成後會自動生成一個download_img的文件夾,打開裏面就是爬取的內容.很少嗶嗶，看代碼。

# @Time    : 2018/4/5 00:49
# @Author  : G_SANGSK/Goseiei 
 
import urllib.request
import urllib.parse
from lxml import etree
import ssl
import os
 
def loadPage(url):
    """
        做用：根據url發送請求，獲取服務器響應文件
        url: 須要爬取的url地址
    """
 
    #headers = {"User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"}
 
    request = urllib.request.Request(url)
    html = urllib.request.urlopen(request).read()
    # 解析HTML文檔爲HTML DOM模型
    content = etree.HTML(html)
    #print content
    # 返回全部匹配成功的列表集合
    link_list = content.xpath('//div[@class="t_con cleafix"]/div/div/div/a/@href')
 
    #link_list = content.xpath('//a[@class="j_th_tit"]/@href')
    for link in link_list:
        fulllink = "http://tieba.baidu.com" + link
        # 組合爲每一個帖子的連接
        # print(link)
        loadImage(fulllink)
 
 
# 取出每一個帖子裏的每一個圖片鏈接
def loadImage(link):
    headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
    request = urllib.request.Request(link, headers = headers)
    html = urllib.request.urlopen(request).read()
    # 解析
    content = etree.HTML(html)
    # 取出帖子裏每層層主發送的圖片鏈接集合
    #link_list = content.xpath('//img[@class="BDE_Image"]/@src')
    # link_list = content.xpath('//div[@class="post_bubble_middle"]')
    link_list = content.xpath('//img[@class="BDE_Image"]/@src')
    # 取出每一個圖片的鏈接
    for link in link_list:
        print(link)
        writeImage(link)
 
 
def writeImage(link):
    """
        做用：將html內容寫入到本地
        link：圖片鏈接
    """
    #print "正在保存 " + filename
    headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
    # 文件寫入
    request = urllib.request.Request(link, headers = headers)
    # 圖片原始數據
    image = urllib.request.urlopen(request).read()
    # 取出鏈接後10位作爲文件名
    filename = link[-10:]
    filename = "./download_img/" + filename
    # 寫入到本地磁盤文件內
    if not os.path.exists("./download_img"):
        os.mkdir("./download_img")
    with open(filename, "wb") as f:
        f.write(image)
    print("已經成功下載 "+ filename)
 
def tiebaSpider(url, beginPage, endPage):
    """
        做用：貼吧爬蟲調度器，負責組合處理每一個頁面的url
        url : 貼吧url的前部分
        beginPage : 起始頁
        endPage : 結束頁
    """
    for page in range(beginPage, endPage + 1):
        pn = (page - 1) * 50
        #filename = "第" + str(page) + "頁.html"
        fullurl = url + "&pn=" + str(pn)
        #print fullurl
        loadPage(fullurl)
        #print html
 
        print("謝謝使用")
 
if __name__ == "__main__":
    ssl._create_default_https_context = ssl._create_unverified_context
    kw = input("請輸入要爬取貼吧名:")
    beginPage = int(input("請輸起始頁："))
    endPage = int(input("請輸結束頁："))
 
    url = "http://tieba.baidu.com/f?"
    key = urllib.parse.urlencode({"kw": kw})
    fullurl = url + key
    tiebaSpider(fullurl, beginPage, endPage)
 
 
 
   #喜歡的朋友能夠收藏去皮一下.