最近学习go,就找了一个例子练习【go语言爬虫】go语言爬取豆瓣电影top250，思路大概就是获取网页，然后根据页面元素，用正则表达式匹配电影名称、评分、评论人数。原文有个地方需要修改下<code>pattern4 := <img width="100" alt="(.*?)" src=</code>，这样就能运行了
结果截图
这个例子可以由修改下变成并发的形式，提高性能（参考golang 并发 chan）
var sem chan int = make(chan int,10);
for i := 0; i < 10; i++ {
go func(i int) {
header := map[string]string{
"Host": "movie.douban.com",
"Connection": "keep-alive",
"Cache-Control": "max-age=0",
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Referer": "https://movie.douban.com/top250",
}
fmt.Println("正在抓取第" + strconv.Itoa(i) + "页......")
url := "https://movie.douban.com/top250?start=" + strconv.Itoa(i*25) + "&filter="
spider := &Spider{url, header}
html := spider.get_html_header()
pattern2 := `<span>(.*?)评价</span>`
rp2 := regexp.MustCompile(pattern2)
find_txt2 := rp2.FindAllStringSubmatch(html, -1)
pattern3 := `property="v:average">(.*?)</span>`
rp3 := regexp.MustCompile(pattern3)
find_txt3 := rp3.FindAllStringSubmatch(html, -1)
pattern4 := `<img width="100" alt="(.*?)" src=`
rp4 := regexp.MustCompile(pattern4)
find_txt4 := rp4.FindAllStringSubmatch(html, -1)
for i := 0; i < len(find_txt2); i++ {
fmt.Printf("%s %s %s\n", find_txt4[i][1], find_txt3[i][1], find_txt2[i][1], )
f.WriteString(find_txt4[i][1] + "\t" + find_txt3[i][1] + "\t" + find_txt2[i][1] + "\t" + "\r\n")
}
sem <- 0
}(i)
}
for i := 0; i < 10; i++ { <-sem }
close(sem)
并发效果截图
到这里go爬虫部分已经介绍完毕，百无聊赖之际又写了一个python版，python果真是简洁,最后祝大家买买买得开心
# coding=utf-8 #
import re
import urllib2
import datetime
def getDouban(i):
print "爬取第" + str(i)+"页"
html = "https://movie.douban.com/top250?start=" + str(i) + "&filter="
try:
page = urllib2.urlopen(html, timeout=3)
result = page.read()
score = re.findall('property="v:average">(.*?)</span>',result)
person = re.findall('<span>(.*?)评价</span>',result)
name= re.findall('<img width="100" alt="(.*?)" src=', result)
j=0
while j<len(name):
print name[j], score[j]+'分', person[j]
j=j+1
except:
print i
starttime = datetime.datetime.now()
params=[]
for i in range(25):
getDouban(i)
endtime = datetime.datetime.now()
print "爬虫历时"+str((endtime-starttime).seconds)+"s完成"
python版运行结果
