想爬点知乎图片结果抱一堆错
一、pip install bs4时报错:
Fatal error in launcher: Unable to create process using '"c:\users\administrator\desktop\1\scripts\python.exe" "D:\BaiduSyncdisk\code\python\1\Scripts\pip.exe" install bs4',
所以就python -m pip install -U pip了一下,再安装bs4时就成功了,
接着尝试爬取,报错bs4.FeatureNotFound: Couldn't find a tree builder with the features you requested: lxml. Do you need to install a parser library?
然后安装lxml
在运行就好了
代码附上
import requests
from bs4 import BeautifulSoup
from requests.exceptions import RequestException
import os
import re
url = "----------------改成你的网址---------------------"
os.makedirs(r"-----------改成你的保存路径------------")
def get_one_page(url):
try:
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36 Edg/114.0.1823.82"
}
# 请求头要添加,不然访问失败
response = requests.get(url, headers=headers)
if response.status_code == 200:
return response.text
# 返回页面html文本
return None
except RequestException:
return None
def get_image_url(html):
soup = BeautifulSoup(html, "lxml")
items = soup.select("figure")
# 将figure节点选择出来
"""for i in range(1,4):
print(items[i])"""
return items
def save_image(item, i):
try:
os.chdir(r"-----------改成你的保存路径------------")
# 改变工作目录
pattern = re.compile('<noscript>.*?data-original="(.*?)".*?</noscript>', re.S)
# 构建正则表达式
image_url = re.search(pattern, str(item))
# 因为item格式为<soup.tag>,要转换成string
r = requests.get(image_url.group(1))
if r.status_code == 200:
file_path = str(i) + ".jpg"
with open(file_path, "wb") as f:
f.write(r.content)
except requests.ConnectionError:
print("Failed to save image")
def main():
html = get_one_page(url)
image_urls = get_image_url(html)
i = 0
for image_url in image_urls:
i += 1
save_image(image_url, i)
print("page", i)
main()