Microwave and RF magazine by kiavash

recipes/microwave_and_rf.recipe

@@ -0,0 +1,217 @@
+#!/usr/bin/env  python
+##
+## Title:        Microwave and RF
+##
+## License:      GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html
+
+# Feb 2012: Initial release
+
+__license__   = 'GNU General Public License v3 - http://www.gnu.org/copyleft/gpl.html'
+'''
+mwrf.com
+'''
+
+import re
+from calibre.web.feeds.news import BasicNewsRecipe
+from calibre.utils.magick import Image
+
+class Microwave_and_RF(BasicNewsRecipe):
+
+    Convert_Grayscale = False # Convert images to gray scale or not
+
+    # Add sections that want to be excluded from the magazine
+    exclude_sections = []
+
+    # Add sections that want to be included from the magazine
+    include_sections = []
+
+    title            = u'Microwave and RF'
+    __author__       = 'kiavash'
+    description      = u'Microwave and RF Montly Magazine'
+    publisher        = 'Penton Media, Inc.'
+    publication_type = 'magazine'
+    site             = 'http://mwrf.com'
+
+    language = 'en'
+    asciiize = True
+    timeout = 120
+    simultaneous_downloads = 1 # very peaky site!
+
+    # Main article is inside this tag
+    keep_only_tags = [dict(name='table', attrs={'id':'prtContent'})]
+
+    no_stylesheets = True
+    remove_javascript = True
+
+    # Flattens all the tables to make it compatible with Nook
+    conversion_options = {'linearize_tables' : True}
+
+    remove_tags    = [
+                        dict(name='span', attrs={'class':'body12'}),
+                     ]
+
+    remove_attributes = [ 'border', 'cellspacing', 'align', 'cellpadding', 'colspan',
+                          'valign', 'vspace', 'hspace', 'alt', 'width', 'height' ]
+
+    # Specify extra CSS - overrides ALL other CSS (IE. Added last).
+    extra_css = 'body { font-family: verdana, helvetica, sans-serif; } \
+                 .introduction, .first { font-weight: bold; } \
+                 .cross-head { font-weight: bold; font-size: 125%; } \
+                 .cap, .caption { display: block; font-size: 80%; font-style: italic; } \
+                 .cap, .caption, .caption img, .caption span { display: block; margin: 5px auto; } \
+                 .byl, .byd, .byline img, .byline-name, .byline-title, .author-name, .author-position, \
+                    .correspondent-portrait img, .byline-lead-in, .name, .bbc-role { display: block; \
+                    font-size: 80%; font-style: italic; margin: 1px auto; } \
+                 .story-date, .published { font-size: 80%; } \
+                 table { width: 100%; } \
+                 td img { display: block; margin: 5px auto; } \
+                 ul { padding-top: 10px; } \
+                 ol { padding-top: 10px; } \
+                 li { padding-top: 5px; padding-bottom: 5px; } \
+                 h1 { font-size: 175%; font-weight: bold; } \
+                 h2 { font-size: 150%; font-weight: bold; } \
+                 h3 { font-size: 125%; font-weight: bold; } \
+                 h4, h5, h6 { font-size: 100%; font-weight: bold; }'
+
+    # Remove the line breaks and float left/right and picture width/height.
+    preprocess_regexps     = [(re.compile(r'<br[ ]*/>', re.IGNORECASE), lambda m: ''),
+                              (re.compile(r'<br[ ]*clear.*/>', re.IGNORECASE), lambda m: ''),
+                              (re.compile(r'float:.*?'), lambda m: ''),
+                              (re.compile(r'width:.*?px'), lambda m: ''),
+                              (re.compile(r'height:.*?px'), lambda m: '')
+                              ]
+
+
+    def print_version(self, url):
+        url = re.sub(r'.html', '', url)
+        url = re.sub('/ArticleID/.*?/', '/Print.cfm?ArticleID=', url)
+        return url
+
+    # Need to change the user agent to avoid potential download errors
+    def get_browser(self, *args, **kwargs):
+       from calibre import browser
+       kwargs['user_agent'] = 'Mozilla/5.0 (Windows NT 5.1; rv:10.0) Gecko/20100101 Firefox/10.0'
+       return browser(*args, **kwargs)
+
+
+    def parse_index(self):
+
+        # Fetches the main page of Microwave and RF
+        soup = self.index_to_soup(self.site)
+
+        # Searches the site for Issue ID link then returns the href address
+        # pointing to the latest issue
+        latest_issue = soup.find('a', attrs={'href':lambda x: x and 'IssueID' in x}).get('href')
+
+        # Fetches the index page for of the latest issue
+        soup = self.index_to_soup(latest_issue)
+
+        # Finds the main section of the page containing cover, issue date and
+        # TOC
+        ts = soup.find('div', attrs={'id':'columnContainer'})
+
+        # Finds the issue date
+        ds = ' '.join(self.tag_to_string(ts.find('span', attrs={'class':'CurrentIssueSectionHead'})).strip().split()[-2:]).capitalize()
+        self.log('Found Current Issue:', ds)
+        self.timefmt = ' [%s]'%ds
+
+        # Finds the cover image
+        cover = ts.find('img', src = lambda x: x and 'Cover' in x)
+        if cover is not None:
+            self.cover_url = self.site + cover['src']
+            self.log('Found Cover image:', self.cover_url)
+
+        feeds = []
+        article_info = []
+
+        # Finds all the articles (tiles and links)
+        articles = ts.findAll('a', attrs={'class':'commonArticleTitle'})
+
+        # Finds all the descriptions
+        descriptions = ts.findAll('span', attrs={'class':'commonCopy'})
+
+        # Find all the sections
+        sections = ts.findAll('span', attrs={'class':'kicker'})
+
+        title_number = 0
+
+        # Goes thru all the articles one by one and sort them out
+        for section in sections:
+            title_number = title_number + 1
+
+            # Removes the unwanted sections
+            if self.tag_to_string(section) in self.exclude_sections:
+                continue
+
+            # Only includes the wanted sections
+            if self.include_sections:
+                if self.tag_to_string(section) not in self.include_sections:
+                    continue
+
+
+            title = self.tag_to_string(articles[title_number])
+            url = articles[title_number].get('href')
+            if url.startswith('/'):
+                    url = self.site + url
+
+            self.log('\tFound article:', title, 'at', url)
+            desc = self.tag_to_string(descriptions[title_number])
+            self.log('\t\t', desc)
+
+            article_info.append({'title':title, 'url':url, 'description':desc,
+                                'date':self.timefmt})
+
+        if article_info:
+            feeds.append((self.title, article_info))
+
+        #self.log(feeds)
+        return feeds
+
+    def postprocess_html(self, soup, first):
+        if self.Convert_Grayscale:
+            #process all the images
+            for tag in soup.findAll(lambda tag: tag.name.lower()=='img' and tag.has_key('src')):
+                iurl = tag['src']
+                img = Image()
+                img.open(iurl)
+                if img < 0:
+                    raise RuntimeError('Out of memory')
+                img.type = "GrayscaleType"
+                img.save(iurl)
+        return soup
+
+    def preprocess_html(self, soup):
+
+        # Includes all the figures inside the final ebook
+        # Finds all the jpg links
+        for figure in soup.findAll('a', attrs = {'href' : lambda x: x and 'jpg' in x}):
+
+            # makes sure that the link points to the absolute web address
+            if figure['href'].startswith('/'):
+                figure['href'] = self.site + figure['href']
+
+            figure.name = 'img' # converts the links to img
+            figure['src'] = figure['href'] # with the same address as href
+            figure['style'] = 'display:block' # adds /n before and after the image
+            del figure['href']
+            del figure['target']
+
+        # Makes the title standing out
+        for title in soup.findAll('a', attrs = {'class': 'commonSectionTitle'}):
+            title.name = 'h1'
+            del title['href']
+            del title['target']
+
+        # Makes the section name more visible
+        for section_name in soup.findAll('a', attrs = {'class': 'kicker2'}):
+            section_name.name = 'h5'
+            del section_name['href']
+            del section_name['target']
+
+        # Removes all unrelated links
+        for link in soup.findAll('a', attrs = {'href': True}):
+            link.name = 'font'
+            del link['href']
+            del link['target']
+
+        return soup