python爬虫实战

python爬虫实战

1.爬取知乎某页html

# 导入urllib库的urlopen函数
from urllib.request import urlopen 
# 发出请求，获取html
html = urlopen("https://zhuanlan.zhihu.com/p/77560712")
# 获取的html内容是字节，将其转化为字符串
html_text = bytes.decode(html.read())
# 打印html内容
print(html_text)

运行结果：
该页的html

2.笔趣阁小说网址写入data.txt

import requests
from lxml import etree

url = "https://www.xbiquge.la/"
headers = {'User-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36 Edg/91.0.864.67'}


def main():
    html_text = requests.get(url = url, headers = headers).text
    #解析

    #先实例化一个etree对象
    html_etree_object = etree.HTML(html_text)

    passage_title_list1 = html_etree_object.xpath("//div/dl/dt/a[@href]")
    passage_addre_list1 = html_etree_object.xpath("//dt/a/@href")

    fp = open('data.txt','w',encoding='utf-8')

    # print(passage_title_list1)
    # print(passage_addre_list1)
    # print(passage_title_list1[0].xpath('./text()'))
#局部解析并写入文件
    for (ti,ad) in zip(passage_title_list1,passage_addre_list1):
        fp.write(ti.xpath("./text()")[0] + ":" + ad + '\n')
    fp.close()

main()

输出data.txt结果：
大夏文圣:https://www.ibiquge.la/98/98990/
机武风暴:https://www.ibiquge.la/34/34606/
高天之上:https://www.ibiquge.la/96/96419/
明克街13号:https://www.ibiquge.la/90/90492/
斗罗大陆5重生唐三:https://www.ibiquge.la/24/24770/
恐怖复苏:https://www.ibiquge.la/21/21210/
万古神帝:https://www.ibiquge.la/7/7552/
穷鬼的上下两千年:https://www.ibiquge.la/15/15550/
我家娘子，不对劲:https://www.ibiquge.la/96/96930/
灵境行者:https://www.ibiquge.la/47/47167/

爬取图片网站，把图片写入文件夹

import requests
from lxml import etree
import os

def get_picture():
    try:
        url = "https://pic.netbian.com/4kdongman/index_2.html"
        headers = {'User-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.106 Safari/537.36'}
        #抓取网页
        html_pic = requests.get(url = url , headers = headers)
        #查看状态码,若不是200返回异常
        html_pic.raise_for_status()
        #编码utf-8
        html_pic.encoding = html_pic.apparent_encoding
        #使用xpath数据解析
        html_text = html_pic.text
        etree_html = etree.HTML(html_text)
        li_list = etree_html.xpath('//div[@class="slist"]/ul/li')
        #创建文件夹
        if not os.path.exists('./pictures1'):
            os.mkdir('./pictures1')
        #写入文件picture1
        for li in li_list:
            #局部解析出图片地址和名字
            pic_add ="https://pic.netbian.com/" + li.xpath("./a/img/@src")[0]#注意xpath返回一个列表所以取下标[0]，而且返回的地址不完全，所以在网址上打开看一下，把少的域名补上
            pic_name = li.xpath("./a/img/@alt")[0] + '.jpg'
            img_data = requests.get(url = pic_add,headers = headers).content
            img_path = "pictures1/" + pic_name
            with open(img_path,'ab') as fp:
                fp.write(img_data)
                print(pic_name,"保存成功！")
                fp.close()
    except:
        return"产生异常"
def main():
    get_picture()


main()