Python爬取百度贴吧图片脚本

Posted 2022-11-09 wy_0928

新手，以下是爬取百度贴吧制定帖子的图片脚本，因为脚本主要是解析html代码，因此一旦百度修改页面前端代码，那么脚本会失效，权当爬虫入门练习吧，后续还会尝试更多的爬虫。

# coding=utf-8
# !/usr/bin/env python
import urllib, string, os
from bs4 import BeautifulSoup

def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

def getImg():
    imgPath = 'F:/craw_tieba/'
    if not os.path.exists(imgPath):
        os.makedirs(imgPath)
    baseUrl = 'http://tieba.baidu.com/p/4657665666'
    imgList = []
    for pg in range(1, 114):
        url = baseUrl + '?pn=' + str(pg)
        print 'Craw: ',url
        html = getHtml(url)
        soup = BeautifulSoup(html)
        imgURLList = string.split(str(soup.find_all('img')), ',')
        for i in range(0, len(imgURLList)):
            if 'http://imgsrc.baidu.com/forum/w%3D580/sign=' in imgURLList[i]:
                start = string.find(imgURLList[i], 'http')
                end = string.find(imgURLList[i], '.jpg') + 4
                imgList.append(imgURLList[i][start : end])
    x = 1
    for img in imgList:
        urllib.urlretrieve(img, 'F:/craw_tieba/%s.jpg' % x)
        x += 1
    print 'Craw tieba finish!'

if __name__ == '__main__':
    getImg()