#2 assignment

WebScrapingStudy · Mar 24, 2019 · 46ecb51 · 46ecb51
1 parent 5b22b31
commit 46ecb51
Show file tree

Hide file tree

Showing 8 changed files with 75 additions and 0 deletions.
diff --git a/2주차/박가나/01_bs4.py b/2주차/박가나/01_bs4.py
@@ -0,0 +1,8 @@
+import bs4
+
+html_str = "<html><div></div></html>"
+bsObj = bs4.BeautifulSoup(html_str, "html.parser")
+
+print(type(bsObj))
+print(bsObj)
+print(bsObj.find("div"))
diff --git a/2주차/박가나/02_urlopen.py b/2주차/박가나/02_urlopen.py
@@ -0,0 +1,6 @@
+import urllib.request
+
+url = "https://www.naver.com"
+html = urllib.request.urlopen(url)
+
+print(html.read())
diff --git a/2주차/박가나/03_naver_parsing.py b/2주차/박가나/03_naver_parsing.py
@@ -0,0 +1,15 @@
+import urllib.request
+import bs4
+
+url = "https://www.naver.com"
+html = urllib.request.urlopen(url)
+
+bsObj = bs4.BeautifulSoup(html, "html.parser")
+
+# print(html.read())
+# print(bsObj)
+
+top_right = bsObj.find("div", {"class" : "area_links"})
+first_a = top_right.find("a")
+
+print(first_a.text)
diff --git a/2주차/박가나/04_naver_menu.py b/2주차/박가나/04_naver_menu.py
@@ -0,0 +1,16 @@
+import urllib.request
+import bs4
+
+url = "https://www.naver.com"
+html = urllib.request.urlopen(url)
+
+bsObj = bs4.BeautifulSoup(html, "html.parser")
+
+ul = bsObj.find("ul", {"class" : "an_l"})
+
+lis = ul.findAll("li")
+
+for li in lis :
+    a_tag = li.find("a")
+    span = a_tag.find("span",{"class" : "an_txt"})
+    print(span.text)
diff --git a/2주차/박가나/05_naver_news.py b/2주차/박가나/05_naver_news.py
@@ -0,0 +1,15 @@
+from urllib.request import urlopen
+import bs4
+
+url = "http://news.naver.com"
+html = urlopen(url)
+
+bsObj = bs4.BeautifulSoup(html, "html.parser")
+
+ul = bsObj.find("ul", {"id" : "text_today_main_news_801001"})
+
+lis = ul.findAll("li")
+
+for li in lis :
+    strong = li.find("strong")
+    print(strong.text)
diff --git a/2주차/박가나/assignment.py b/2주차/박가나/assignment.py
@@ -0,0 +1,15 @@
+import urllib.request
+import bs4
+
+url = "https://comic.naver.com/index.nhn"
+html = urllib.request.urlopen(url)
+
+bsObj = bs4.BeautifulSoup(html, "html.parser")
+
+div = bsObj.find("div", {"class" : "tab_gr"})
+
+lis = div.findAll("li")
+
+for li in lis :
+    a_tag = li.find("a")
+    print(a_tag.text)
diff --git a/2주차/박가나/cmd창.JPG b/2주차/박가나/cmd창.JPG
diff --git a/2주차/박가나/인터넷창.JPG b/2주차/박가나/인터넷창.JPG