Shershnev Pavel

Task-1.py

@@ -0,0 +1,29 @@
+import json
+import xml.etree.ElementTree as ET
+from urllib.request import urlopen
+
+
+def main():
+    data = urlopen('https://lenta.ru/rss').read().decode('utf8')
+    root = ET.fromstring(data)
+    items = root.find('channel').findall('item')
+    tags = ['pubDate', 'title']
+    create_json(items, tags, 'news.json')
+
+
+def create_json(items, tags, filename):
+    result = []
+    for item in items:
+        for i in range(len(tags)-1):
+            result.append(
+                {
+                    tags[i]: item.find(tags[i]).text,
+                    tags[i+1]: item.find(tags[i+1]).text
+                 }
+            )
+    with open(filename, 'w', encoding='utf8') as file:
+        json.dump(result, file, indent=1, ensure_ascii=False)
+
+
+if __name__ == '__main__':
+    main()

Task-2.py

@@ -0,0 +1,43 @@
+import json
+import xml.etree.ElementTree as ET
+from urllib.request import urlopen
+
+
+def main():
+    data = urlopen('https://lenta.ru/rss').read().decode('utf8')
+    root = ET.fromstring(data)
+    items = root.find('channel').findall('item')
+    tags = ['pubDate', 'title']
+    create_json(items, tags, 'news.json')
+    parse_items(items, 'news1.json')
+
+
+def create_json(items, tags, filename):
+    result = []
+    for item in items:
+        for i in range(len(tags)-1):
+            result.append(
+                {
+                    tags[i]: item.find(tags[i]).text,
+                    tags[i+1]: item.find(tags[i+1]).text
+                 }
+            )
+    with open(filename, 'w', encoding='utf8') as file:
+        json.dump(result, file, indent=1, ensure_ascii=False)
+
+
+def parse_items(items, filename):
+    result = []
+    for item in items:
+        data = {}
+        for i in item.iter():
+            if i == item:
+                continue
+            data[i.tag] = i.text
+        result.append(data)
+    with open(filename, 'w', encoding='utf8') as file:
+        json.dump(result, file, indent=1, ensure_ascii=False)
+
+
+if __name__ == '__main__':
+    main()

Task-3.py

@@ -0,0 +1,29 @@
+from urllib.request import urlopen
+from json import loads
+import itertools
+import datetime
+
+
+def main():
+    url = 'https://ru.wikipedia.org/w/api.php?action=query&format=json&prop=revisions&rvlimit=500&titles=%D0%93%D1%80%D0%B0%D0%B4%D1%81%D0%BA%D0%B8%D0%B9,_%D0%90%D0%BB%D0%B5%D0%BA%D1%81%D0%B0%D0%BD%D0%B4%D1%80_%D0%91%D0%BE%D1%80%D0%B8%D1%81%D0%BE%D0%B2%D0%B8%D1%87'
+    get_statistic(url, '183903', 'revisions.txt')
+
+
+def get_statistic(url, page_id, filename):
+    data = loads(urlopen(url).read().decode('utf8'))
+    sorted_revisions = sorted(data['query']['pages'][page_id]['revisions'], key=get_date, reverse=True)
+    groups = itertools.groupby(sorted_revisions, get_date)
+    statistics = {}
+    for date, group in groups:
+        statistics[date] = list(group)
+    with open(filename, 'w', encoding='utf8') as file:
+        for date in statistics:
+            print(date, len(statistics[date]), file=file)
+
+
+def get_date(x):
+    return datetime.datetime.strptime(x['timestamp'], '%Y-%m-%dT%H:%M:%SZ').date()
+
+
+if __name__ == '__main__':
+    main()

Task-4.py

@@ -0,0 +1,30 @@
+from urllib.request import urlopen
+from json import loads
+import itertools
+import datetime
+
+
+def main():
+    url = 'https://ru.wikipedia.org/w/api.php?action=query&format=json&prop=revisions&rvlimit=500&titles=%D0%91%D0' \
+           '%B5%D0%BB%D1%8C%D0%BC%D0%BE%D0%BD%D0%B4%D0%BE,_%D0%96%D0%B0%D0%BD-%D0%9F%D0%BE%D0%BB%D1%8C '
+    get_statistic(url, '192203', 'revisions1.txt')
+
+
+def get_statistic(url, page_id, filename):
+    data = loads(urlopen(url).read().decode('utf8'))
+    sorted_revisions = sorted(data['query']['pages'][page_id]['revisions'], key=get_date, reverse=True)
+    groups = itertools.groupby(sorted_revisions, get_date)
+    statistics = {}
+    for date, group in groups:
+        statistics[date] = list(group)
+    with open(filename, 'w', encoding='utf8') as file:
+        for date in statistics:
+            print(date, len(statistics[date]), file=file)
+
+
+def get_date(x):
+    return datetime.datetime.strptime(x['timestamp'], '%Y-%m-%dT%H:%M:%SZ').date()
+
+
+if __name__ == '__main__':
+    main()