@@ -1,87 +0,0 @@
1−"""
2− Twitter (Social media)
3−
4− @website https://twitter.com/
5− @provide-api yes (https://dev.twitter.com/docs/using-search)
6−
7− @using-api no
8− @results HTML (using search portal)
9− @stable no (HTML can change)
10− @parse url, title, content
11−
12− @todo publishedDate
13−"""
14−
15−from urllib.parse import urlencode, urljoin
16−from lxml import html
17−from datetime import datetime
18−from searx.utils import extract_text
19−
20−# engine dependent config
21−categories = ['social media']
22−language_support = True
23−
24−# search-url
25−base_url = 'https://twitter.com/'
26−search_url = base_url + 'search?'
27−
28−# specific xpath variables
29−results_xpath = '//li[@data-item-type="tweet"]'
30−avatar_xpath = './/img[contains(@class, "avatar")]/@src'
31−link_xpath = './/small[@class="time"]//a'
32−title_xpath = './/span[contains(@class, "username")]'
33−content_xpath = './/p[contains(@class, "tweet-text")]'
34−timestamp_xpath = './/span[contains(@class,"_timestamp")]'
35−
36−
37−# do search-request
38−def request(query, params):
39− params['url'] = search_url + urlencode({'q': query})
40−
41− # set language if specified
42− if params['language'] != 'all':
43− params['cookies']['lang'] = params['language'].split('-')[0]
44− else:
45− params['cookies']['lang'] = 'en'
46−
47− return params
48−
49−
50−# get response from search-request
51−def response(resp):
52− results = []
53−
54− dom = html.fromstring(resp.text)
55−
56− # parse results
57− for tweet in dom.xpath(results_xpath):
58− try:
59− link = tweet.xpath(link_xpath)[0]
60− content = extract_text(tweet.xpath(content_xpath)[0])
61− img_src = tweet.xpath(avatar_xpath)[0]
62− img_src = img_src.replace('_bigger', '_normal')
63− except Exception:
64− continue
65−
66− url = urljoin(base_url, link.attrib.get('href'))
67− title = extract_text(tweet.xpath(title_xpath))
68−
69− pubdate = tweet.xpath(timestamp_xpath)
70− if len(pubdate) > 0:
71− timestamp = float(pubdate[0].attrib.get('data-time'))
72− publishedDate = datetime.fromtimestamp(timestamp, None)
73− # append result
74− results.append({'url': url,
75− 'title': title,
76− 'content': content,
77− 'img_src': img_src,
78− 'publishedDate': publishedDate})
79− else:
80− # append result
81− results.append({'url': url,
82− 'title': title,
83− 'content': content,
84− 'img_src': img_src})
85−
86− # return results
87− return results