-
Notifications
You must be signed in to change notification settings - Fork 99
/
Copy pathvideos.json
160 lines (160 loc) · 7.41 KB
/
videos.json
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
[
{
"video": {
"videoId": "y7FbFJ4jOW8",
"title": "Intro to Web Scraping using ScrapFly SDK and Python",
"publishingDate": "Jul 17, 2024",
"lengthSeconds": 994,
"keywords": null,
"description": "https://scrapfly.io/ \nhttps://scrapfly.io/docs/sdk/python\n\nThe code used in the video:\nhttps://github.com/scrapfly/sdk-demo\n\nFor more web scraping tutorials, see our blog:\n• Scraping with Python and BeautifulSoup\nhttps://scrapfly.io/blog/web-scraping-with-python-beautifulsoup/\n• Parsing HTML with XPath\nhttps://scrapfly.io/blog/parsing-html-with-xpath/\n• Parsing HTML with CSS selectors\nhttps://scrapfly.io/blog/parsing-html-with-css/\n\nSections:\n00:00 introduction\n00:14 setup \n00:25 Use Overview\n01:25 HTML parser\n01:55 Cache feature\n02:09 Debug feature\n02:26 Request options\n03:00 Anti Scraping Blocking bypass\n03:24 Proxies\n03:50 Cloud Web Browsers\n04:31 Browser Control\n04:50 Extraction API\n08:09 Screenshot API\n10:18 Example Project Overview\n10:46 Setup\n11:32 Scraping Yelp Business Pages\n12:23 Parsing Business Pages\n13:26 Example Scrape Run\n14:04 Scraping Yelp Search\n14:49 Parsing Search Pages\n15:22 Example Scrape Run\n15:48 Summary",
"thumbnail": [
{
"url": "https://i.ytimg.com/vi/y7FbFJ4jOW8/hqdefault.jpg?sqp=-oaymwEbCKgBEF5IVfKriqkDDggBFQAAiEIYAXABwAEG&rs=AOn4CLA5GZvRYNzbZLUhgoRY_2J6y_XdqQ",
"width": 168,
"height": 94
},
{
"url": "https://i.ytimg.com/vi/y7FbFJ4jOW8/hqdefault.jpg?sqp=-oaymwEbCMQBEG5IVfKriqkDDggBFQAAiEIYAXABwAEG&rs=AOn4CLC_K8zCt7q4cG91mY3es1l67tI8EA",
"width": 196,
"height": 110
},
{
"url": "https://i.ytimg.com/vi/y7FbFJ4jOW8/hqdefault.jpg?sqp=-oaymwEcCPYBEIoBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLBX5dVuSqyj64sOedXyu12O0L9onw",
"width": 246,
"height": 138
},
{
"url": "https://i.ytimg.com/vi/y7FbFJ4jOW8/hqdefault.jpg?sqp=-oaymwEcCNACELwBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLD3xuZsWo83LE0s-xxbhvm2otSRjA",
"width": 336,
"height": 188
}
],
"stats": {
"viewCount": 811,
"likeCount": 10,
"commentCount": 2
}
},
"channel": {
"name": "Scrapfly",
"identifierId": "UCoX3U_dywuQf_KbLhWoUCmw",
"id": "@scrapfly",
"verified": false,
"channelUrl": "https://www.youtube.com/@scrapfly",
"subscriberCount": "47 subscribers",
"thumbnails": [
{
"url": "https://yt3.ggpht.com/-1WidfW2QQpH4gwy7zm2Rmw2w5yE9MWIS7mn30R7yeEf2BQwG0czf6QeYIwvOIYG1q9X-VXi0g=s88-c-k-c0x00ffffff-no-rj"
}
]
},
"commentContinuationToken": "Eg0SC3k3RmJGSjRqT1c4GAYyJSIRIgt5N0ZiRko0ak9XODAAeAJCEGNvbW1lbnRzLXNlY3Rpb24%3D"
},
{
"video": {
"videoId": "muo6I9XY8K4",
"title": "Use AI to extract data from documents using Scrapfly Extraction API",
"publishingDate": "Jul 11, 2024",
"lengthSeconds": 374,
"keywords": [
"ai",
"web-scraping",
"data-parsing",
"scrapfly"
],
"description": "Introduction to using Scrapfly Extraction API for extracting data from document. \nSee https://github.com/scrapfly/llm-scraping-demo for notebook source code of these examples.\n\nSections:\n00:00 introduction\n00:40 setup \n00:56 LLM Extraction\n01:47 Scrape API\n01:57 Different Prompt Types\n02:22 Real-life LLM examples\n03:20 Auto Parser\n04:10 Extraction Rules\n05:00 Outro",
"thumbnail": [
{
"url": "https://i.ytimg.com/vi/muo6I9XY8K4/hqdefault.jpg?sqp=-oaymwEbCKgBEF5IVfKriqkDDggBFQAAiEIYAXABwAEG&rs=AOn4CLAIf9b3EuJAmZQp41OMcxpS_Vm92w",
"width": 168,
"height": 94
},
{
"url": "https://i.ytimg.com/vi/muo6I9XY8K4/hqdefault.jpg?sqp=-oaymwEbCMQBEG5IVfKriqkDDggBFQAAiEIYAXABwAEG&rs=AOn4CLDmXNQmo-iGD3H_5NWEhKbYRYYRtw",
"width": 196,
"height": 110
},
{
"url": "https://i.ytimg.com/vi/muo6I9XY8K4/hqdefault.jpg?sqp=-oaymwEcCPYBEIoBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLBLhpgUlglnlFPjcR8nSyNjPNqNgA",
"width": 246,
"height": 138
},
{
"url": "https://i.ytimg.com/vi/muo6I9XY8K4/hqdefault.jpg?sqp=-oaymwEcCNACELwBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLDNyMaZyA3SFHEISHIgrPf5KxIjiw",
"width": 336,
"height": 188
}
],
"stats": {
"viewCount": 354,
"likeCount": 3,
"commentCount": null
}
},
"channel": {
"name": "Scrapfly",
"identifierId": "UCoX3U_dywuQf_KbLhWoUCmw",
"id": "@scrapfly",
"verified": false,
"channelUrl": "https://www.youtube.com/@scrapfly",
"subscriberCount": "47 subscribers",
"thumbnails": [
{
"url": "https://yt3.ggpht.com/-1WidfW2QQpH4gwy7zm2Rmw2w5yE9MWIS7mn30R7yeEf2BQwG0czf6QeYIwvOIYG1q9X-VXi0g=s88-c-k-c0x00ffffff-no-rj"
}
]
},
"commentContinuationToken": "Eg0SC211bzZJOVhZOEs0GAYyJSIRIgttdW82STlYWThLNDAAeAJCEGNvbW1lbnRzLXNlY3Rpb24%3D"
},
{
"video": {
"videoId": "1Y-XvvWlyzk",
"title": "Capture screenshots of any website using Scrapfly's Screenshot API - Introduction",
"publishingDate": "Jul 9, 2024",
"lengthSeconds": 271,
"keywords": null,
"description": "introduction to Scrapfly's Screenshot API for capturing screenshots of websites on demand for data analysis and event tracking. See https://github.com/scrapfly/screenshot-scraping-demo for notebook source code of examples used in this video.\n\nSections:\n00:00 introduction\n00:21 setup \n01:00 Basic use\n01:26 Capture parameter\n01:42 Resolution parameter\n02:10 Capture areas\n02:40 Javascript execution\n03:08 Auto_scroll parameter\n03:25 Options parameter\n03:35 Block Banners\n03:46 Dark mode option\n04:00 Cache parameter\n04:20 Web Player & Outro",
"thumbnail": [
{
"url": "https://i.ytimg.com/vi/1Y-XvvWlyzk/hqdefault.jpg?sqp=-oaymwEbCKgBEF5IVfKriqkDDggBFQAAiEIYAXABwAEG&rs=AOn4CLBUoNTV2OPYjB5OeuT9bc5jXopB8A",
"width": 168,
"height": 94
},
{
"url": "https://i.ytimg.com/vi/1Y-XvvWlyzk/hqdefault.jpg?sqp=-oaymwEbCMQBEG5IVfKriqkDDggBFQAAiEIYAXABwAEG&rs=AOn4CLBLQ6IfEtgdDHn2U3glQNPBngzpDg",
"width": 196,
"height": 110
},
{
"url": "https://i.ytimg.com/vi/1Y-XvvWlyzk/hqdefault.jpg?sqp=-oaymwEcCPYBEIoBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLBz7SVQLL7vf6kS04bEQQQFKjcajg",
"width": 246,
"height": 138
},
{
"url": "https://i.ytimg.com/vi/1Y-XvvWlyzk/hqdefault.jpg?sqp=-oaymwEcCNACELwBSFXyq4qpAw4IARUAAIhCGAFwAcABBg==&rs=AOn4CLDP6i14YjIFKijcdMJUDLvhVKVA-w",
"width": 336,
"height": 188
}
],
"stats": {
"viewCount": 296,
"likeCount": 4,
"commentCount": null
}
},
"channel": {
"name": "Scrapfly",
"identifierId": "UCoX3U_dywuQf_KbLhWoUCmw",
"id": "@scrapfly",
"verified": false,
"channelUrl": "https://www.youtube.com/@scrapfly",
"subscriberCount": "47 subscribers",
"thumbnails": [
{
"url": "https://yt3.ggpht.com/-1WidfW2QQpH4gwy7zm2Rmw2w5yE9MWIS7mn30R7yeEf2BQwG0czf6QeYIwvOIYG1q9X-VXi0g=s88-c-k-c0x00ffffff-no-rj"
}
]
},
"commentContinuationToken": "Eg0SCzFZLVh2dldseXprGAYyJSIRIgsxWS1YdnZXbHl6azAAeAJCEGNvbW1lbnRzLXNlY3Rpb24%3D"
}
]