0fweek

import requests
from lxml import etree
# User-Agent:Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36

def body():
    url = "https://gongkong.ofweek.com/2019-04/ART-310058-11000-30318953.html"
    header = {'User-Agent':'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36'}
    respones = requests.get(url,headers=header)
    print(respones)
    respones.encoding = "gbk"
    html = respones.text
    obj = etree.HTML(html)
    obj_titer = obj.xpath('//div[@class="artical"]/p/text()')
    print(obj_titer)
    obj_body = obj.xpath('//div[@id="articleC"]/p//text()')
    print(obj_body)
    '''提取图片'''
    obj_1_picture = obj.xpath('//div[@id="articleC"]/p/img/@src')
    print(obj_1_picture)
    """
     翻页
    """
    obj_page = obj.xpath('//div[@class="page"]/span/a/@href')[0]
    print(obj_page)
    obj_page_link = 'https://gongkong.ofweek.com/2019-05/' + obj_page
    print(obj_page_link)
    respones_2 = requests.get(obj_page_link,headers=header)
    print(respones_2)
    respones_2.encoding = "gbk"
    html_2 = respones_2.text
    obj_2 = etree.HTML(html_2)
    obj_2_body = obj_2.xpath('//div[@id="articleC"]/p//text()')
    print(obj_2_body)
    object = obj_titer + obj_body + obj_2_body
    '''提取图片'''
    obj_2_picture = obj_2.xpath('//div[@id="articleC"]/p/img/@src')
    print(obj_2_picture)


    """为保存文件的换行 空格"""
    v = []
    for i in object:
        v.append("\u3000"+"\u3000" + i+"\n")

    """文件头"""
    y = []
    for i in obj_titer:
        s = i.strip()
        y.append(s)
    res = str(y)[2:12]   #列表转字符串形式
    print(res)

    with open(r"F:\day08\人民日报\微信图片\%s.txt"%res,"w",encoding="utf-8") as f:
         for i in v:
             f.write(i)

    '''保存图片'''
    obj_picture = obj_1_picture + obj_2_picture
    print(obj_picture)
    ret = len(obj_picture)
    print(ret)
    s = range(0,ret)
    for i,d in zip(obj_picture,s):
        reg = requests.get(i)
        with open(r"F:\day08\人民日报\微信图片\%s.jpg"%d,"wb",) as f:

            f.write(reg.content)
body()

　　

转载于:https://www.cnblogs.com/heluobing/p/10928745.html