[已解决]关于爬虫的问题

Mr丶张

最近学了一点爬虫但是不知道这个为什么这个程序一直报错

import urllib.request
from lxml import etree

def create_response(page):
    if 1 == page:
        url = 'https://sc.chinaz.com/tu/meinv.html'
    else:
        str(page)
        url = "https://sc.chinaz.com/tu/meinv-%s-0-0.html"%page

    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36"
    }

    response = urllib.request.Request(url, headers = headers)

    return response

def get_info(response):
    request = urllib.request.urlopen(response)
    content = request.read().decode('utf-8')

    return content

def down_img(content):
    tree = etree.HTML(content)
    nameList = tree.xpath('//div[@id="ulcontent"]//div//img/@alt')
    imgList = tree.xpath('//div[@id="ulcontent"]//div//img/@data-src')

    for i in range(len(nameList) - 1):
        img = 'https:' + imgList[i]
        name = nameList[i]
        print(img)
        # urllib.request.urlretrieve(img, name + '.jpg')
    print("Over")

if __name__ == '__main__':
    startPage = int(input("请输入开始页:"))
    endPage = int(input("请输入结束页:"))

    for page in range(startPage, endPage + 1):
        response = create_response(page)
        content = get_info(response)
        down_img(content)

最佳答案

月排行榜 / 总排行榜

临时号

2022-6-12 00:47:19

Mr丶张 发表于 2022-6-12 00:21
34行的注释解开了会报错

注意:你的网址中有\,应当全部替换为/

import urllib.request
from lxml import etree

def create_response(page):
    if 1 == page:
        url = 'https://sc.chinaz.com/tu/meinv.html'
    else:
        str(page)
        url = "https://sc.chinaz.com/tu/meinv-%s-0-0.html"%page

    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36"
    }

    response = urllib.request.Request(url, headers = headers)

    return response

def get_info(response):
    request = urllib.request.urlopen(response)
    content = request.read().decode('utf-8')

    return content

def down_img(content):
    tree = etree.HTML(content)
    nameList = tree.xpath('//div[@id="ulcontent"]//div//img/@alt')
    imgList = tree.xpath('//div[@id="ulcontent"]//div//img/@data-src')

    for i in range(len(nameList) - 1):
        img = 'https:' + imgList[i]
        name = nameList[i]
        print(img)
        urllib.request.urlretrieve(img.replace("\","/"), name + '.jpg')  # 注意:你的网址中有\,应当全部替换为/
    print("Over")

if __name__ == '__main__':
    startPage = int(input("请输入开始页:"))
    endPage = int(input("请输入结束页:"))

    for page in range(startPage, endPage + 1):
        response = create_response(page)
        content = get_info(response)
        down_img(content)

跳转到最佳答案楼层

Mr丶张

34行的注释解开了会报错

临时号

我运行一切正常啊

临时号

Mr丶张 发表于 2022-6-12 00:21
34行的注释解开了会报错

注意:你的网址中有\,应当全部替换为/

import urllib.request
from lxml import etree

def create_response(page):
    if 1 == page:
        url = 'https://sc.chinaz.com/tu/meinv.html'
    else:
        str(page)
        url = "https://sc.chinaz.com/tu/meinv-%s-0-0.html"%page

    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36"
    }

    response = urllib.request.Request(url, headers = headers)

    return response

def get_info(response):
    request = urllib.request.urlopen(response)
    content = request.read().decode('utf-8')

    return content

def down_img(content):
    tree = etree.HTML(content)
    nameList = tree.xpath('//div[@id="ulcontent"]//div//img/@alt')
    imgList = tree.xpath('//div[@id="ulcontent"]//div//img/@data-src')

    for i in range(len(nameList) - 1):
        img = 'https:' + imgList[i]
        name = nameList[i]
        print(img)
        urllib.request.urlretrieve(img.replace("\","/"), name + '.jpg')  # 注意:你的网址中有\,应当全部替换为/
    print("Over")

if __name__ == '__main__':
    startPage = int(input("请输入开始页:"))
    endPage = int(input("请输入结束页:"))

    for page in range(startPage, endPage + 1):
        response = create_response(page)
        content = get_info(response)
        down_img(content)

临时号

Mr丶张 发表于 2022-6-12 00:21
34行的注释解开了会报错

问题解决了吗?