2019-09-17 14:14:01 3912浏览
今天千锋扣丁学堂Python培训老师给大家分享一篇关于爬取知乎图片代码实现解析的详细介绍,首先,需要获取任意知乎的问题,只需要你输入问题的ID,就可以获取相关的页面信息,比如最重要的合计有多少人回答问题。import requests
import re
import pymongo
import time
DATABASE_IP = '127.0.0.1'
DATABASE_PORT = 27017
DATABASE_NAME = 'sun'
client = pymongo.MongoClient(DATABASE_IP,DATABASE_PORT)
db = client.sun
db.authenticate("dba", "dba")
collection = db.zhihuone # 准备插入数据
BASE_URL = "https://www.zhihu.com/question/{}"
def get_totle_answers(article_id):
headers = {
"user-agent": "需要自己补全 Mozilla/5.0 (Windows NT 10.0; WOW64)"
}
with requests.Session() as s:
with s.get(BASE_URL.format(article_id),headers=headers,timeout=3) as rep:
html = rep.text
pattern =re.compile( '<meta itemProp="answerCount" content="(\d*?)"/>')
s = pattern.search(html)
print("查找到{}条数据".format(s.groups()[0]))
return s.groups()[0]
if __name__ == '__main__':
# 用死循环判断用户输入的是否是数字
article_id = ""
while not article_id.isdigit():
article_id = input("请输入文章ID:")
totle = get_totle_answers(article_id)
if int(totle)>0:
zhi = ZhihuOne(article_id,totle)
zhi.run()
else:
print("没有任何数据!")
完善图片下载部分,图片下载地址在查阅过程中发现,存在json字段的content中,我们采用简单的正则表达式将他匹配出来。细节如下图展示:
def download_img(self,data):
## 下载图片
for item in data["data"]:
content = item["content"]
pattern = re.compile('<noscript>(.*?)</noscript>')
imgs = pattern.findall(content)
if len(imgs) > 0:
for img in imgs:
match = re.search('<img src="(.*?)"', img)
download = match.groups()[0]
download = download.replace("pic3", "pic2") # 小BUG,pic3的下载不到
print("正在下载{}".format(download), end="")
try:
with requests.Session() as s:
with s.get(download) as img_down:
# 获取文件名称
file = download[download.rindex("/") + 1:]
content = img_down.content
with open("imgs/{}".format(file), "wb+") as f: # 这个地方进行了硬编码
f.write(content)
print("图片下载完成", end="\n")
except Exception as e:
print(e.args)
else:
pass
运行结果为:
【关注微信公众号获取更多学习资料】 【扫码进入Python全栈开发免费公开课】