Regular Expressions and crawling are webpage Images

Regular Expression

Namespace: using system. Text. regularexpressions;

Common classes:

RegEx

Matchcollection

Match

Group

Groupcollection

Common Methods:

RegEx. ismatch (); Return Value bool

RegEx. Match (); Return Value match

RegEx. Matches (); Return Value matchcollection

RegEx. Replace (); Return Value string

Regular Expressions capture images:

Reference namespace: using system. net;

Using system. IO;

Ideas: 1. Get all the information on the web page from the Internet, 2. Use Regular Expressions for matching and obtain the specific address of the image to be obtained, 3. Download;

Static void Mian (string [] ARGs)

{

WebClient WC = new WebClient ();

String html = WC. downloadstring (@ "--- page --- ");

Matchcollect MC = RegEx. Matches (HTML, @ "<\ s? IMG [^>] + src = "" ([^ ""] +) "); // use a regular expression for matching, because there are many images, therefore, it is common to store a list set;

List <string> PIC = new list <string> ();

Foreach (Match m in MC) // traverse

{

If (M. Success) // If the matching string can be placed in the PIC set

{

PIC. Add (M. Group [1]. value. Trim (); // obtain the image src = "~~~ "Form; extract image name

}

}

String url = @ "webpage address ";

For (INT I = 0; I <PIC. Count; I ++)

{

String temp = PIC [I];

Temp = URL +/+ temp; // Add the URL address before the image name;

PIC [I] = temp; // re-change the image name in the PIC set. This image is a complete webpage image address.

}

String address = "target location to download ";

If (! Directory. exists (Address) // first, you can determine whether a folder is used in the disk.

{

Directory. createdirectory ("file ");

}

Else

{

For (INT I = 0; I <PIC. Count. I ++)

{

String name = RegEx. Match (PIC [I], @ "./(. +)"). Groups [1]. value;

// RegEx. Match (PIC [I], @ "./(. +)"); for matching, display the image name "/~~~ "Form;

// RegEx. match (PIC [I], @ ". /(. + )"). groups [1]. the value captures the image name, which is created to be the same as the online name during download;

WC. downloadfile (PIC [I], path. Combine (address, name); // download complete

}

}

Console. readkey ();

}