优化爬取百度图库：可改存储地址，命名
import reimport urllib
import requests
import os
def get_onepage_urls(onepageurl):
"""获取单个翻页的所有图片的urls+当前翻页的下一翻页的url"""
if not onepageurl:
print('已到最后一页, 结束')
return[], ''
try:
html = requests.get(onepageurl).text
except Exception as e:
print(e)
pic_urls = []
fanye_url = ''
return pic_urls, fanye_url
pic_urls = re.findall('"objURL":"(.*?)",', html, re.S)
fanye_urls = re.findall(re.compile(r'<a href="(.*)" class="n">下一页</a>'), html, flags=0)
fanye_url = 'http://image.baidu.com' + fanye_urls if fanye_urls else ''
return pic_urls, fanye_url
def down_pic(pic_urls,path):
"""给出图片链接列表, 下载所有图片"""
s = 0
for i, pic_url in enumerate(pic_urls):
try:
pic = requests.get(pic_url, timeout=15)
string = str(i + 1)+'.jpg'
s = i + 1
with open(path+keyword+ str(i+1) + ".jpg", "ab") as f:
f.write(pic.content)
print('成功下载第%s张图片: %s' % (str(i + 1), str(pic_url)))
except Exception as e:
print('下载第%s张图片时失败: %s' % (str(i + 1), str(pic_url)))
s = i+1
print(e)
continue
print("下载完成！")
if __name__ == '__main__':
keyword = input("请输入搜索关键词：")# 关键词, 改为你想输入的词即可, 相当于在百度图片里搜索一样
url_init_first = r'http://image.baidu.com/search/flip?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1497491098685_R&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&ctd=1497491098685%5E00_1519X735&word='
url_init = url_init_first + urllib.parse.quote(keyword, safe='/')
all_pic_urls = []
onepage_urls, fanye_url = get_onepage_urls(url_init)
all_pic_urls.extend(onepage_urls)
fanye_count = 0# 累计翻页数
n=input("请输入翻页数：")
if os.path.isdir("F:\Python爬取\图片/"+keyword) != True:#如果保存的路径不存在
os.makedirs(r"F:\Python爬取\图片/"+keyword)#如果不存在。我们将创立这个路径
path = "F:\Python爬取\图片/"+keyword+"/"
while fanye_count<int(n):
onepage_urls, fanye_url = get_onepage_urls(fanye_url)
fanye_count += 1
print('第%s页' % fanye_count)
if fanye_url == '' and onepage_urls == []:
break
all_pic_urls.extend(onepage_urls)
down_pic(list(set(all_pic_urls)),path) 这。。。。。。 为什么有requests库了还用urllib库 收藏学习
收藏学习，看看
页:
[1]