lecture 7 link

vojtechkaniaedu · Mar 30, 2021 · be78186 · be78186
1 parent a6113ab
commit be78186
Show file tree

Hide file tree

Showing 3 changed files with 228 additions and 2,379 deletions.
diff --git a/06_seminar/exercises.ipynb b/06_seminar/exercises.ipynb
@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -36,12 +36,21 @@
    "source": [
     "### 1a. Request Quandl for time series `FB` from `WIKI` database. Use JSON format.\n",
     "\n",
-    "Hint: https://www.quandl.com/api/v3/datasets/{QUANDL_DATABASE}/{QUANDL_DATASET}/data.{DATA_FORMAT}?api_key={YOUR-QUANDL-API-KEY}"
+    "Hint: https://www.quandl.com/api/v3/datasets/{QUANDL_DATABASE}/{QUANDL_DATASET}/data.{DATA_FORMAT}?api_key={YOUR-QUANDL-API-KEY}\n",
+    "\n",
+    "Use GET"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": []
@@ -57,7 +66,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": []
@@ -80,6 +89,20 @@
    "outputs": [],
    "source": []
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -115,6 +138,13 @@
    "outputs": [],
    "source": []
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -203,7 +233,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -213,12 +243,13 @@
     "\n",
     "    Make sure that the request object is parsed as UTF-8 string.\n",
     "    '''\n",
+    "    r = requests.get(link,encoding='UTF-8')\n",
     "    pass"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -231,13 +262,14 @@
     "    The URLs are expected in absolute format, i.e. including a full domain.\n",
     "    '''\n",
     "    pass\n",
-    "\n",
-    "    "
+    "    \n",
+    "news_links = get_all_news_links('https://ies.fsv.cuni.cz/content/tree/index/lang/en')\n",
+    "news_links"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -250,22 +282,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "def parse_date(soup):\n",
     "    '''\n",
     "    Parse text of the sibling of sibling of the first h3 element in the soup. Note that the immidiate sibling of `h3` is not Tag element, but NavigableString. This is used to represent text between tags.\n",
     "    '''\n",
-    "\n",
     "    pass\n",
     "    "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -277,13 +308,15 @@
     "\n",
     "    Hint: Consider using a `.join()` function applicable on string object\n",
     "    '''\n",
-    "\n",
-    "    pass"
+    "    \n",
+    "    pass\n",
+    "    \n",
+    "print(parse_news_content(get_soup('https://ies.fsv.cuni.cz/en/news/4976')))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -298,23 +331,33 @@
     "\n",
     "    time.sleep(pause)\n",
     "    \n",
-    "    pass"
+    "    pass\n",
+    "    \n",
+    "parse_ies_news('https://ies.fsv.cuni.cz/en/news/4976')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 62,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "def get_all_news(link):\n",
     "    '''\n",
-    "    wraping fuctions that accepts a `link` pointing towards hub website with links to parse and returing a dataframe containing all the links\n",
+    "    wraping fuction that accepts a `link` pointing towards hub website with links to parse and returing a dataframe containing all the links\n",
     "    '''\n",
-    "\n",
-    "    pass"
+    "    \n",
+    "    pass\n",
+    "df = get_all_news('https://ies.fsv.cuni.cz/content/tree/index/lang/en')"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -340,8 +383,7 @@
     "        pass\n",
     "\n",
     "\n",
-    "dl = Downloader('https://ies.fsv.cuni.cz/content/tree/index/lang/en')\n",
-    "dl.df"
+    "#dl = Downloader('https://ies.fsv.cuni.cz/content/tree/index/lang/en')\n"
    ]
   },
   {

diff --git a/07_Pandas/lecture7.ipynb b/07_Pandas/lecture7.ipynb
diff --git a/README.md b/README.md
@@ -1,5 +1,5 @@
 # Data Processing in Python (JEM207)
-The seminar on Monday March 29th will be held online on the following Google Meet: meet.google.com/mqh-quhp-wsj
+The lecture on Tuesday March 30rd will be held online on the following Google Meet: meet.google.com/kvo-hgyp-crb
 
 The course site for the Data Processing in Python from [IES](http://ies.fsv.cuni.cz/). See information on [SIS](https://is.cuni.cz/studium/predmety/index.php?do=predmet&kod=JEM207). The course is taught by [Martin Hronec](mailto:martin.hronec@fsv.cuni.cz), [Vítek Macháček](mailto:vit.machacek@cerge-ei.cz) and [Jan Šíla](mailto:jan.sila@fsv.cuni.cz).