Merge pull request #13 from kvakanet/master

Исправления от @kvakanet Изменено составление url с http на https Исправлено формирования url на автора(и добавлен новый метод author_url) Добавлены методы для получения некоторых мета данных и стилей и добавления их в PDF Исправлено маштабирование изображений Чуть-чуть обновил библиотеки для проекта
author: icoz <icoz.vt@gmail.com> 2017-02-12 16:32:22 +0300
committer: GitHub <noreply@github.com> 2017-02-12 16:32:22 +0300
commit: c66b4859fa5244a166cefd96761fc8360a5fe3b8 (patch)
tree: 08b8c0be285cdc3e76588ce1a1a98d7e1e30bb1f
parent: 8cd076fe9f58bdab7e45c54a6d5a035eb4fb2264 (diff)
parent: 37f4f3c2bce7bcd3049c3f814fe226cfde7ccde6 (diff)
4 files changed, 58 insertions, 11 deletions
diff --git a/README.md b/README.md
index afbc220..18ee00c 100644
--- a/README.md
+++ b/README.md
@@ -36,6 +36,11 @@ Usage:
 ```
 
 Changelog:
+*12.02.2017*
+- Добавлены мета теги для лучшего поиска PDF
+- Исправлена вставка автора(вставляется ссылка на автора рабочая)
+- Решана проблема с маштабированием изображений
+
 *01.02.2015*
 - исправлены ошибки
 - добавлена поддержка Geektimes.ru и Megamozg.ru
diff --git a/habr/topic.py b/habr/topic.py
index 5436d1f..fdf56f9 100644
--- a/habr/topic.py
+++ b/habr/topic.py
@@ -31,7 +31,7 @@ class TMTopic(object):
         return self.url
 
     def _getTopicUrl(self, topic_id):
-        return str('http://{domain}/post/{tid}/').format(domain=self.domain, tid=topic_id)
+        return str('https://{domain}/post/{tid}/').format(domain=self.domain, tid=topic_id)
 
     def _parseTopic(self):
         '''
@@ -53,7 +53,27 @@ class TMTopic(object):
         tmp = doc.xpath("//div[@class='author-info__username']//a[@class='author-info__nickname']") or \
               doc.xpath("//div[@class='author-info__username']//a[@class='author-info__name']") or \
               doc.xpath("//div[@class='author-info__username']//span[@class='author-info__name']")
-        self.post['author'] = tmp[0].text if len(tmp) else ''
+        if len(tmp):
+            self.post['author_url'] = ('https://' + self.domain + tmp[0].attrib['href'] )
+            self.post['author'] = tmp[0].text
+        else:
+            self.post['author_url']= ''
+            self.post['author'] = ''
+        ###
+        post_desc = doc.xpath("//meta[@name='description']/@content")
+        self.post['desc'] = post_desc[0].strip("\r\n")
+        #
+        tmp = doc.xpath("//link[@rel='stylesheet'][@media='all']")
+        style = '\n'.join([ str(etree.tostring(st,pretty_print=True, method='html').decode('utf-8')).strip("\n\r") for st in tmp ])
+        self.post['styles'] = style if len(style)>2 else ''
+        #
+        #tmp = doc.xpath("//style[@type='text/css']")
+        #style =''.join([ str(etree.tostring(st,pretty_print=True, method='html').decode('utf-8')) for st in tmp ])
+        #self.post['styles'] += style if (len(style)>2) else ''
+        #
+        post_keywords = doc.xpath("//meta[@name='keywords']/@content")
+        self.post['keywords'] = post_keywords[0].strip("\r\n")
+        ###
         # bug in class 'infopanel ' - space added
         tmp = doc.xpath(
             "//ul[@class='postinfo-panel postinfo-panel_post']//span[@class='oting-wjt__counter-score js-score']")
@@ -109,7 +129,19 @@ class TMTopic(object):
 
     def author(self):
         return deepcopy(self.post['author'])
+###
+    def author_url(self):
+        return deepcopy(self.post['author_url'])
+
+    def desc(self):
+        return deepcopy(self.post['desc'])
+
+    def styles(self):
+        return deepcopy(self.post['styles'])
 
+    def keywords(self):
+        return deepcopy(self.post['keywords'])
+###
     def text(self):
         return deepcopy(self.post['text'])
 
diff --git a/habraparse.py b/habraparse.py
index 2f3f8e6..c455089 100755
--- a/habraparse.py
+++ b/habraparse.py
@@ -55,16 +55,23 @@ def prepare_html(topic, with_comments=False):
     <meta http-equiv="content-type" content="text/html; charset=utf-8">
     <meta charset="UTF-8">
     <title>{title}</title>
+    <meta name="author" content="{author}">
+    <meta name="generator" content="habraparse">
+    <meta name="description" content="{desc}">
+    <meta name="keywords" content="{keywords}">
     </head>
     <body>
     <div id="layout">
     <div class="inner">
         <div class="content_left">
-            <div class="post_show">
-                <div class="post shortcuts_item">
+            <!-- <div class="post_show"> -->
+            <div class="post__body post__body_full">
+                <!-- <div class="post shortcuts_item"> -->
+                <div class="content html_format">
                     <h1 class="title"><span class="post_title">{title}</span></h1>
                     <div class="author">
-                        <a title="Автор текста" href="http://habrahabr.ru/users/{author}/" >{author}</a>
+                        <!-- <a title="Автор текста" href="http://habrahabr.ru/users/{author}/" >{author}</a> -->
+                        <a title="Автор текста" href="{author_url}" >{author}</a>
                     </div>
                     {text}
                 </div>
@@ -89,11 +96,13 @@ def prepare_html(topic, with_comments=False):
     '''
     if with_comments:
         html_format = html_head + html_cmnts + html_foot
-        html = html_format.format(title=t.title(), author=t.author(), text=t.text(),
+        html = html_format.format(title=t.title(), author=t.author(), author_url=t.author_url(), desc=t.desc(), text=t.text(),
+                                  addstyle=t.styles(), keywords=t.keywords(),
                                   comments=generate_comments(t.comments(), 0), cmnts_count=t.comments_count())
     else:
         html_format = html_head + html_foot
-        html = html_format.format(title=t.title(), author=t.author(), text=t.text())
+        html = html_format.format(title=t.title(), author=t.author(), author_url=t.author_url(), desc=t.desc(), text=t.text(),
+                                  addstyle=t.styles(), keywords=t.keywords() )
     html = str(html).replace('"//habrastorage.org', '"https://habrastorage.org')
     return html
 
@@ -137,7 +146,8 @@ def save_pdf(topic_id: int, filename: str, with_comments: bool = False, project:
         ht = HabraTopic(topic_id)
 
     html = prepare_html(ht, with_comments=with_comments)
-    css = CSS(string='@page { size: A4; margin: 1cm !important}')
+    css = CSS(string='@page { size: A4; margin: 1cm; !important;} img { width: 100%; height: auto; !important; }')
+    #css = CSS(string='@page { size: A4 landscape; margin: 1cm !important}')
     HTML(string=html).write_pdf(filename, stylesheets=[css])
 
 
diff --git a/requirements.txt b/requirements.txt
index ddad416..83aed1c 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,5 @@
-cairocffi==0.7.2
-CairoSVG==2.0.0
+cairocffi>=0.7.2
+CairoSVG>=2.0.0
 cffi==1.9.1
 cssselect==1.0.0
 docopt==0.6.2
@@ -11,5 +11,5 @@ Pyphen==0.9.4
 requests==2.12.3
 six==1.10.0
 tinycss==0.4
-WeasyPrint==0.33
+WeasyPrint>=0.34
 webencodings==0.5
author	icoz <icoz.vt@gmail.com>	2017-02-12 16:32:22 +0300
committer	GitHub <noreply@github.com>	2017-02-12 16:32:22 +0300
commit	c66b4859fa5244a166cefd96761fc8360a5fe3b8 (patch)
tree	08b8c0be285cdc3e76588ce1a1a98d7e1e30bb1f
parent	8cd076fe9f58bdab7e45c54a6d5a035eb4fb2264 (diff)
parent	37f4f3c2bce7bcd3049c3f814fe226cfde7ccde6 (diff)