package main
import (
"encoding/json"
"flag"
"fmt"
"github.com/PuerkitoBio/goquery"
"github.com/golang/glog"
"github.com/tealeg/xlsx"
"io/ioutil"
"math/rand"
"net/http"
"strings"
"time"
)
type movie struct {
Directors []string `json:"directors"`
Rate string `json:"rate"`
Rover_x int `json:"cover_x"`
Star string `json:"star"`
Title string `json:"title"`
Url string `json:"url"`
Casts []string `json:"casts"`
Cover string `json:"cover"`
Id string `json:"id"`
Cover_y int `json:"cover_y"`
}
type data struct {
Data []movie `json:"data"`
}
var (
file *xlsx.File
//爬到的影片总数
number int
filePath string = "C:\\Users\\Administrator\\Desktop\\豆瓣.xlsx"
//影视评分
Score = flag.Float64("score", 0, "score")
//分页
Page = flag.Int("page", 0, "page")
//影视类型
Type = flag.String("type", "电影", "type")
)
func getAndParseHtml(movieUrl string) error {
doc, err := goquery.NewDocument(mo
golang 简单爬虫,245行代码爬取豆瓣电影电视剧等信息并保存到excel
最新推荐文章于 2025-06-05 17:29:45 发布