Use of Go language crawler goquery and grequests

Source: Internet
Author: User
Tags sprintf

/* Download Tool */package main import ("FMT"//go language version of jquery "Github.com/puerkitobio/goquery" "OS" "s Ync "Strings"//go language version of Request "Github.com/levigross/grequests" "Time" "StrConv") VAR wg sy nc. Waitgroup Func Main () {now: = time.          Now () Initalurls: = []string{' http://www.zngirls.com/girl/18071/album/',} for _, url: = Range initalurls { Doc, Err: = Goquery. NewDocument (URL) if err! = Nil {fmt. Errorf ("Download error:% #v", err) OS. Exit ( -1)} doc. Find (". Igalleryli_link"). Each (func (i int, S *goquery. Selection) {src, exists: = S.find ("img"). Attr ("src") fmt. Printf ("Start download album Image:%v\n", SRC) if (exists) {WG. ADD (1) Go func (src string) {defer WG.                      Done ()//download image//trytimes: = map[int]int N: = 0 S: = STrings. Replace (SRC, "cover/", "", 1) SS: = Strings. Split (S, "/") FM: = Strings.                        Join (Ss[:len (ss)-1], "/") SF0: = fm + "/%d.jpg" SFN: = fm + "/%03d.jpg"  for {//continuous download S: = "" if n = = 0 {s = fmt. Sprintf (SF0, N)} else {s = fmt. Sprintf (SFN, N)} fmt. Printf ("Ready to Download:%v\n", s) res, _: = Grequests. Get (S, &grequests. requestoptions{//struct can give a value to a specified type, not necessarily a value headers:map[string]strin g{"Referer": "Http://www.zngirls.com", "user-agent": "Moz illa/5.0 (Windows NT 6.1; WOW64) applewebkit/537.36 (khtml, like Gecko) chrome/50.0.2661.102 Safari/537.36 "}})//conditions need to be modified, if no picture, return is hotlinking, picture 4kb if Res. StatusCode! = + FMT. Printf ("Download failed, exit album download:%s\n", SRC) Break}/ /Picture may be the site, return the hotlinking picture (around 4kb) Length: = Res. Header.get ("Content-length") slen,_: = StrConv. Atoi (length) if Slen < 4100{FMT.                            Printf ("Download failed, exit album download:%s\n", SRC) Break} Index: = strings. Index (S, "gallery") if index = =-1 {fmt.                            Errorf ("Invalid address, unable to find gallery keyword, parse failed:%s\n", SRC) return} SS2: = Strings. Split (String (s[index:]), "/") dirname: = Strings.              Join (Ss2[:len (SS2)-1], "/")            If _, Err: = OS. Stat (dirname); Err! = Nil {fmt. Printf ("Create download folder:%s\n", dirname) os. Mkdirall (DirName, 0666)} filename: = strings. Join (SS2, "/") Res. Downloadtofile (filename) fmt.              PRINTF ("Successfully downloaded image to:%s\n", filename) n++}} (SRC) }})} WG. Wait ()//4m bandwidth download, need 16m36s, total size 202m,10 folders, 560 files FMT. Printf ("Download task completed, time consuming:% #v \ n", when. Now ().   Sub (now)}

The use of the Go Language crawler goquery and grequests

Related Article

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.