python - 如何让我的爬虫从起始页解析数据

Question

我用 python 编写了一些代码来从 torrent 站点获取详细信息。然而，当我运行代码时，我发现结果符合我的预期。这个爬虫的唯一问题是它会跳过第一页的内容 [因为分页 URL 从 2 开始]，这是我无法修复的。对此的任何帮助都将非常感激。

import requests
from lxml import html

page_link = "https://yts.ag/browse-movies"
b_link = "https://yts.ag"

def get_links(main_link):
    response = requests.get(main_link).text
    tree = html.fromstring(response)
    for item in tree.cssselect('ul.tsc_pagination a'):
        if "page" in item.attrib["href"]:
            movie_details(b_link + item.attrib["href"])

def movie_details(link):
    response = requests.get(link).text
    tree = html.fromstring(response)
    for titles in tree.cssselect("div.browse-movie-wrap"):
        title = titles.cssselect('div.browse-movie-bottom a.browse-movie-title')[0].text
        link = titles.cssselect('div.browse-movie-year')[0].text
        rating= titles.cssselect('figcaption.hidden-xs h4.rating')[0].text
        genre = titles.cssselect('figcaption.hidden-xs h4')[0].text
        genre1 = titles.cssselect('figcaption.hidden-xs h4')[1].text
        print(title, link, rating, genre, genre1)

get_links(page_link)

Answer 1

为什么不在循环之前调用 main_link 上的 movie_details() 函数？

def get_links(main_link):
    response = requests.get(main_link).text
    tree = html.fromstring(response)
    movie_details(main_link)
    for item in tree.cssselect('ul.tsc_pagination a'):
        if "page" in item.attrib["href"]:
            movie_details(b_link + item.attrib["href"])