parsing

4 months ago · dff81a3258
3 changed files with 41 additions and 0 deletions
--- a/web-scraping/example.html
+++ b/web-scraping/example.html
@ -0,0 +1,7 @@
+<html><head><title>The Website Title</title></head>
+<body>
+<p>Download my <strong>Python</strong> book from <a href="http://
+inventwithpython.com">my website</a>.</p>
+<p class="slogan">Learn Python the easy way!</p>
+<p>By <span id="author">Al Sweigart</span></p>
+</body></html>
--- a/web-scraping/google-search.py
+++ b/web-scraping/google-search.py
@ -0,0 +1,19 @@
+#! python3
+# lucky.py - open several Google search results
+
+import requests, sys, webbrowser, bs4
+
+print('Googling...') # display text while downloading the Google page
+res = requests.get('http://google.com/search?q=' +''.join(sys.argv[1:]))
+res.raise_for_status()
+
+# retrieve the top search result links
+soup = bs4.BeautifulSoup(res.text, 'html.parser')
+
+# open a browser tab for each
+linkElems = soup.select('.LC201b h3')
+numOpen = min(5, len(linkElems))
+print('Opening {} links.'.format(numOpen))
+for i in range(numOpen):
+    webbrowser.open('http://google.com' + linkElems[i].get('href'))
+    linkElems[i].get('href')
--- a/web-scraping/parse-html.py
+++ b/web-scraping/parse-html.py
@ -0,0 +1,15 @@
+import requests, bs4
+
+res = requests.get('https://www.nostarch.com') 
+res.raise_for_status()
+
+noStarchSoup = bs4.BeautifulSoup(res.text)
+print(type(noStarchSoup))
+
+print(noStarchSoup.select('#main > p:nth-of-type(2)'))
+print(noStarchSoup.select('p')[1])
+print(noStarchSoup.select('p > a')[0].getText())
+
+
+# https://beautiful-soup-4.readthedocs.io/en/latest/
+