电影下载

# -*- coding:utf-8 -*-
import requests
from lxml import etree
url = "https://www.dy2018.com/html/gndy/dyzz/index.html"
response = requests.get(url)

# 统一网页的编码格式
# 下面这句话最好加上
# response.encoding = response.apparent_encoding

root = etree.HTML(response.text)
page_urls = root.xpath("//select[@name='select']/option/@value")
# print(page_urls)
for url_1 in page_urls:
    url_1 = "https://www.dy2018.com" + url_1   # 每一页的地址
    # 下载
    response = requests.get(url_1)
    root = etree.HTML(response.content)
    a_list = root.xpath("//td[@height='26']/b/a")
    for a in a_list:
        # print(a)
        title = a.xpath("text()")
        if title:
            title = title[0]
        else:
            continue
        # print(title)
        url = a.xpath("@href")
        if url:
            url = url[0]
        else:
            continue
        if not url.startswith("https"):
            url = "https://www.dy2018.com" + url
        movie_response = requests.get(url)
        movie_root = etree.HTML(movie_response.content)
        # helloworld
        # root.xpath("//a/text()")  找到的只是hello
        # root.xpath("//a//text()")  找到的是标签里面的所有文本  hello world
        movie_links = movie_root.xpath("//td[@bgcolor='#fdfddf']//text()")
        print(movie_links)
        print(url_1)

完整代码：

# -*- coding:utf-8 -*-
import requests
from lxml import etree
url = "https://www.dy2018.com/html/gndy/dyzz/index.html"
response = requests.get(url)
# 统一网页的编码格式
# 下面这句话最好加上
# response.encoding = response.apparent_encoding

root = etree.HTML(response.text)
page_urls = root.xpath("//select[@name='select']/option/@value")
# print(page_urls)
for url_1 in page_urls:
    url_1 = "https://www.dy2018.com" + url_1   # 每一页的地址
    # 下载
    response = requests.get(url_1)
    root = etree.HTML(response.content)
    a_list = root.xpath("//td[@height='26']/b/a")
    for a in a_list:
        # print(a)
        title = a.xpath("text()")
        if title:
            title = title[0]
        else:
            continue
        # print(title)
        url = a.xpath("@href")
        if url:
            url = url[0]
        else:
            continue
        if not url.startswith("https"):
            url = "https://www.dy2018.com" + url
        movie_response = requests.get(url)
        movie_root = etree.HTML(movie_response.content)
        # helloworld
        # root.xpath("//a/text()")  找到的只是hello
        # root.xpath("//a//text()")  找到的是标签里面的所有文本  hello world
        movie_links = movie_root.xpath("//td[@bgcolor='#fdfddf']//text()")
        print(movie_links)
        print(url_1)

运行结果：