python学习——xpath

import requests
from lxml import etree

url = ‘https://bj.58.com/beijingzhoubian/ershoufang/?PGTID=0d30000c-0000-1175-8e33-a6e941f8aff5&ClickID=1‘
headers = {
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER‘
}
# 获取源码数据
page_text = requests.get(url=url,headers=headers).text
# 实例化etree对象
tree = etree.HTML(page_text)
# 调用xpath方法,后去li标签列表
li_list = tree.xpath(‘//ul[@class="house-list-wrap"]/li‘)
fp = open(‘58.csv‘,‘w‘,encoding=‘utf-8‘)
#遍历列表
for li in li_list:
    # .开头的意思：进行局部页面解析;./开头表示从li标签开始解析
    title = li.xpath(‘./div[2]/h2/a/text()‘)[0]
    price = li.xpath(‘./div[3]//text()‘)
    #将价格的三个列表拼接为字符串
    price = ‘‘.join(price)
    fp.write(title+‘:‘+price+‘\n‘)
fp.close()
print(‘over‘)

import requests
from lxml import etree
import os
import urllib

url = ‘http://pic.netbian.com/4kmeinv/‘
headers = {
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER‘
}
response = requests.get(url=url,headers=headers)
#response.encoding = ‘utf-8‘
if not os.path.exists(‘./imgs‘):
    os.mkdir(‘./imgs‘)
page_text = response.text

tree = etree.HTML(page_text)
li_list = tree.xpath(‘//dic[@class="slist"]/ul/li‘) # //dic[@class="slist"]//li
for li in li_list:
    img_name = li.xpath(‘./a/b/text()‘)[0]
    # 处理中文乱码
    img_name = img_name.encode(‘iso-8859-1‘).decode(‘gbk‘)
    img_url = ‘http://pic.netbian.com‘ + li.xpath(‘./a/img/@src‘)[0]
    img_path = ‘./imgs/‘ + img_name + ‘.jpg‘
    urllib.request.urlretrieve(url=img_url,filename=img_path)
    print(img_path,‘下载成功‘)

import requests
from lxml import etree
import base64
import urllib

headers = {
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER‘
}
url = ‘http://jandan.net/ooxx‘
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
img_hash_list = tree.xpath(‘//span[@class="img-hash"]/text()‘)
for img_hash in img_hash_list:
    img_url = ‘http:‘ + base64.b64decode(img_hash).decode()
    img_name = img_url.split(‘/‘)[-1]
    urllib.request.urlretrieve(url=img_url,filename=img_name)

import requests
from lxml import etree
import random

headers = {
    ‘Connection‘:‘close‘,# 当请求成功后，马上断开该次请求（及时释放请求池中的资源））
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER‘
}
url = ‘http://sc.chinaz.com/jianli/free-%d.html‘
for page in range(1,4):
    if page == 1:
        new_url = ‘http://sc.chinaz.com/jianli/free.html‘
    else:
        new_url = format(url%page)
    response = requests.get(url=new_url,headers=headers)
    response.encoding = ‘utf-8‘
    page_text = response.text

    tree = etree.HTML(page_text)
    div_list = tree.xpath(‘//div[@id="container"]/div‘)
    for div in div_list:
        detail_url = div.xpath(‘./a/@href‘)[0]
        name = div.xpath(‘./a/img/@alt‘)[0]

        detail_page = requests.get(url=detail_url,headers=headers).text
        tree = etree.HTML(detail_page)
        download_list = tree.xpath(‘//div[@class="clearfix mt20 downlist"]/ul/li/a/@href‘)
        download_url = random.choice(download_list)
        data = requests.get(url=download_url,headers=headers).content
        file_name = name + ‘.rar‘
        with open(file_name,‘wb‘) as fp:
            fp.write(data)
            print(file_name,‘下载成功‘)

import requests
from lxml import etree
import random

headers = {
    ‘Connection‘:‘close‘,# 当请求成功后，马上断开该次请求（及时释放请求池中的资源））
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER‘
}
url = ‘https://www.aqistudy.cn/historydata/‘
page_text = requests.get(url=url,headers=headers).text

tree = etree.HTML(page_text)
li_list = tree.xpath(‘//div[@class="bottom"]/ul/li | //div[@class="bottom"]/ul/div[2]/li‘)
for li in li_list:
    city_name = li.xpath(‘./a/text()‘)[0]
    print(city_name)

import requests

url = ‘https://www.baidu.com/s?wd=ip‘

page_text = requests.get(url=url,headers=headers,proxies={‘https‘:‘36.111.140.6:8080‘}).text

with open(‘./ip.html‘,‘w‘,encoding=‘utf-8‘) as fp:
    fp.write(page_text)