【Python爬虫】采集一个优秀艺术家相互交流的网站——P站（一个正经的网站）

https://www.acg-pixiv.com/tags/459.html

import requests     # 发送网络请求的模块
import parsel       # 提取数据
import re

url_1 = 'https://www.acg-pixiv.com/tags/450.html'
response_1 = requests.get(url_1)

data_html_1 = response_1.text

selector = parsel.Selector(data_html_1)
# 提取链接 属性内容 @属性名称 css xpath re 
href_list = selector.xpath('/html/body/div/div[1]/ul/li/a/@href').getall()
title_list = selector.xpath('/html/body/div/div[1]/ul/li/a/@title').getall()

for info in zip(href_list, title_list):
    # 索引取值 元组
    url_2 = 'https://www.acg-pixiv.com' + info[1]

# content? 获取二进制数据
response_2 = requests.get(url_2).text

selector_2 = parsel.Selector(response_2)
# 图片链接
url = selector_2.xpath('/html/body/div/div[1]/div[1]/div/img[1]/@src').get()
print(url)

# 当这个程序报错的时候
try:
    img_data = requests.get(img_url, timeout=5).content
except:
    # 图片链接改一下
    img_url = img_url.replace('800', '400')
    img_data = requests.get(img_url).content

title = re.sub(r'[\\/:*?"<>|]', '_', info[1])

print(f'---------正在爬取{title}---------')
with open(f'img/{title}.jpg', mode='wb') as f:
    f.write(img_data)